Sarath Chandar @apsarathchandar Twitter profile

Pinned Tweet

Sarath Chandar

28 days

I am very excited to announce @ChandarLab 's fifth annual research symposium! Please join us on August 19th and 20th to learn more about our recent progress in deep learning, reinforcement learning, NLP, continual learning, optimization, and AI for science! 2 days of great talks

2

7

24

Last Seen Profiles

@sisii4bbc

@bedwell_kourt

@mkobosil

@SeerviD

@stwmaniax

@twingoggy

@ng_regl

@bokeplokalmalam

@MonaRosner

@NMIXX20220222

@SikkhP79131

@wmiltti

@DeHellSon

@vid_athe

@barbcrews

@bokeplokalmalam

@pachinkoguam

@bogor_pasu67127

@bokeplokalmalam

@bogor_pasu67127

@bokeplokalmalam

@thekelssimone

@celikcargo

@bogor_pasu67127

@nana11290121

@Stringer4Kate

@weLL_habbit

@P_Breuninger

@pppland000

@PaulFidika

@amanda_hardy_

@wuxijingye

@NickWisniewski8

@19_zv

@stwmaniax

@HSN

Sarath Chandar

@apsarathchandar

2 years

I am very excited to release this primer on lifelong supervised learning: . Lifelong learning is one of the most promising learning paradigms to achieve artificial general intelligence. 1/n

An Introduction to Lifelong Supervised Learning

This primer is an attempt to provide a detailed summary of the different facets of lifelong learning. We start with Chapter 2 which provides a high-level overview of lifelong learning systems. In...

arxiv.org

6

98

582

Sarath Chandar

@apsarathchandar

4 years

I am very excited to release the recordings of my Machine Learning lectures! You can watch the first lecture here: . If you want to follow the course, readings, lecture notes, and assignments will be made available at .

Machine Learning

An introductory course in machine learning by Prof. Sarath Chandar. Please check http://sarathchandar.in/teaching/ml/fall2020/ for the full course and the sc...

www.youtube.com

5

103

436

Sarath Chandar

@apsarathchandar

10 months

I am recruiting MSc and PhD students for Fall 2024. Application deadline is December 01. Please apply through the @Mila_Quebec supervision request process here: . More details about the recruitment process here:

14

98

400

Sarath Chandar

@apsarathchandar

3 years

I am very excited to release the recordings of my Reinforcement Learning lectures! You can watch the first-week lectures here: . If you want to follow the course, readings, lecture notes, and assignments will be made available at

4

68

383

Sarath Chandar

@apsarathchandar

5 years

I am happy to share that I will be joining @polymtl and @MILAMontreal as an Assistant Professor starting mid-Fall 2019! Looking for students to join my group and work on recurrent neural networks, lifelong learning, reinforcement learning, and NLP. 1/2

43

28

362

Sarath Chandar

@apsarathchandar

5 years

I successfully defended my Ph.D. thesis today! A big thanks to several wonderful people who helped me throughout this journey!

31

6

351

Sarath Chandar

@apsarathchandar

4 years

I am happy and proud to officially introduce my research group through this new lab website: . If you are interested in joining us, @MILAMontreal MSc/PhD applications are now open! Deadline: Dec 15. For more info:

6

35

343

Sarath Chandar

@apsarathchandar

2 years

An @OpenAI scientist feeling conflicted about the release of @StableDiffusion that could kill their controlled closedAI business. Of course!

Joshua Achiam ⚗️

@jachiam0

2 years

I feel very conflicted about the Stable Diffusion open source release.

57

184

1K

16

336

Sarath Chandar

@apsarathchandar

3 months

I am happy to announce that I have been promoted to Associate Professor with tenure at @polymtl . This is an achievement for the entire @chandarlab ! I want to thank my awesome students, without whom this would not have been possible! 1/n

37

6

246

Sarath Chandar

@apsarathchandar

11 months

Join my lab! I am currently recruiting new students for admission in the Fall of 2024. If you're interested in working with me, submit your application via Mila's supervision application process. To find out more, click here: @Mila_Quebec

Mila | Supervision Requests

Each student at Mila is supervised by one of our affiliated professors. Applicants are selected through the supervision request process.

mila.quebec

4

50

235

Sarath Chandar

@apsarathchandar

4 years

I am teaching a new graduate-level Machine Learning course @polymtl / @MILAMontreal in Fall 2020 - . The course is online. If you are a student in any of the Quebec Universities, you can register for the course here:

4

35

217

Sarath Chandar

@apsarathchandar

5 years

I am looking for Masters and Ph.D. students to start in Fall 2020. If you are interested in working with me at @MILAMontreal (), the deadline is Dec 15. More info here: . You can also come to talk to me at #NeurIPS2019 .

6

45

218

Sarath Chandar

@apsarathchandar

3 years

I have multiple open MSc/PhD positions on memory augmented neural nets, RL, Lifelong Learning, NLP for Fall 2022 at @ChandarLab / @Mila_Quebec / @polymtl ! Details: Applications due Dec 1st:

4

46

182

Sarath Chandar

@apsarathchandar

1 year

I am truly honored to be named a Canada Research Chair (CRC) in Lifelong Machine Learning in addition to my already existing Canada CIFAR AI Chair by @CIFAR_News ! This is a recognition to all the exceptional work of my students @ChandarLab ! Thank you @NSERC_CRSNG !

Mila - Institut québécois d'IA

@Mila_Quebec

1 year

Congratulations to our Core Academic Member Sarath Chandar, who was appointed Canada Research Chair in Lifelong Machine Learning this week and received a grant from the Canadian government to further his research work. Read the full annoucement :

2

3

33

22

7

154

Sarath Chandar

@apsarathchandar

9 months

I will be at #NeurIPS2023 from 14-17. I am looking to recruit MSc/Phds to work on 1. Optimization for DL and RL. 2. Continual/Lifelong Learning. 3. LLMs. (eps. bias, interpretability) 4. ML/RL for scientific discovery. Email me to meet there if you have relevant background!

2

12

137

Sarath Chandar

@apsarathchandar

4 years

I am teaching a course on scientific and technical communication for CS PhD students this Fall. Please suggest great books, articles, blogs posts on how to read, write, review technical papers, and also how to present your research in an effective way.

19

14

135

Sarath Chandar

@apsarathchandar

8 months

This is the sad state of ML research right now.

Karan Desai (KD)

@kdexd

8 months

I noticed a footnote in this paper. Why the rush? It is strange to arXiv a paper with a "known* bug, but the bug is mentioned in a tiny footnote. This could be fixed by re-training in a few days. We as a community, need to slow down.

8

21

202

0

8

122

Sarath Chandar

@apsarathchandar

6 months

🎉 Excited to announce our work "Recall to Imagine (R2I)" got an oral spot at #ICLR2024 ! R2I is a generalist and computationally efficient agent that shines in RL memory tasks, showing superhuman performance in most complex memory tasks. Kudos to @M_R_Samsami & @artemZholus ! 1/n

4

20

116

Sarath Chandar

@apsarathchandar

4 years

We introduce a new regularizer for CNNs called PatchUP. PatchUP alleviates some of the drawbacks of the previous mixing-based regularizers - . Work led by Mojtaba Faramarzi. We also opensource our code to reproduce the results here: .

GitHub - chandar-lab/PatchUp

Contribute to chandar-lab/PatchUp development by creating an account on GitHub.

github.com

1

23

109

Sarath Chandar

@apsarathchandar

1 year

So these 3 MIT profs think that using the data without consent is the only problem with the paper.

Raunak Chowdhuri

@raunakdoesdev

1 year

FINAL UPDATE: On June 24th, Armando Solar-Lezama (Professor in EECS and COO/Associate Director of CSAIL, MIT), Tonio Buonassisi (Professor of Mechanical Engineering, MIT), and Yoon Kim (Assistant Professor in EECS and CSAIL, MIT) released a public statement regarding the paper.

17

108

609

1

8

106

Sarath Chandar

@apsarathchandar

3 years

Doina Precup, @rpascanu and I are very excited to announce the first International Conference on Lifelong Learning Agents (CoLLA)! If you are working in lifelong/continual learning, meta-learning, multi-task learning, or OOD generalization, consider submitting your work to CoLLA!

CoLLAs 2025

@CoLLAs_Conf

3 years

We are thrilled to announce a new focused #MachineLearning conference: International Conference on Lifelong Learning Agents (CoLLA) 1/

6

163

635

1

21

107

Sarath Chandar

@apsarathchandar

10 months

At @ChandarLab , we are happy to announce the launch of our assistantce program to provide feedback for members of communities underrepresented in AI who wants to apply to high-profile graduate programs. Want feedback? Details: . Deadline: Nov 15!

3

24

101

Sarath Chandar

@apsarathchandar

2 years

Time to stop stereotyping India like this! Just look around. All your major companies (including this Twitter) are run by Indians and that should give you some clue.

T Wolf 🌁

@Twolfrecovery

2 years

This isn't a shanty town in India. This is Oakland, CA. The crisis of our generation. #homelessness

2K

4K

10K

6

88

Sarath Chandar

@apsarathchandar

5 years

Attention MAY NOT be all you need. You also need recurrence. Interesting work by Chinnadhurai Sankar and Sandeep Subramanian: #ACL2019

Do Neural Dialog Systems Use the Conversation History Effectively?...

Neural generative models have been become increasingly popular when building conversational agents. They offer flexibility, can be easily adapted to new domains, and require minimal domain...

arxiv.org

0

21

87

Sarath Chandar

@apsarathchandar

4 years

Inspired by @kchonyc , I will be doing free-of-charge pro-bono office hours to talk with organizations that have the need for Artificial Intelligence ( #AI ) and Machine Learning ( #ML ) but does not have in-house expertise in AI/ML. For more details:

Sarath Chandar Pro-bono Office Hour Request

I spend 1 hour per week to talk with an organization who has the need for Artificial Intelligence (AI) and Machine Learning (ML) but does not have in-house expertise in AI/ML. If you are one of these...

docs.google.com

4

17

88

Sarath Chandar

@apsarathchandar

4 years

Are you tired of manually creating new tasks for Lifelong RL? We introduce Lifelong Hanabi in which every task is coordinating with a partner that's an expert player of Hanabi. Work led by @HadiNekoei and @akileshbadri . paper: @Mila_Quebec 1/n

1

17

85

Sarath Chandar

@apsarathchandar

5 years

Our work on training RNNs for lifelong learning got accepted at Neural Computation! Joint work with @shagunsodhani and Yoshua Bengio. The paper discusses how can we tackle both catastrophic forgetting and capacity saturation jointly.

Towards Training Recurrent Neural Networks for Lifelong Learning

Catastrophic forgetting and capacity saturation are the central challenges of any parametric lifelong learning system. In this work, we study these challenges in the context of sequential...

arxiv.org

1

6

82

Sarath Chandar

@apsarathchandar

4 months

If someone wants to do AI research in India, this is definitely the best place to do so! I’m looking forward to all the great work that is going to come out of Wadhwani School of Data Science and AI..

Balaraman Ravindran

@ravi_iitm

4 months

Starting on an exciting journey at the new Wadhwani School of Data Science and AI. The video summarizes the motivation for starting the school. Come join us in enriching the Data Science and AI ecosystem at @iitmadras . @rbc_dsai_iitm @cerai_iitm @IBSE_IITM @ai4bharat @DSAI_IITM

10

23

167

1

6

69

Sarath Chandar

@apsarathchandar

3 months

I am very proud and happy to announce that our @ChandarLab MSc graduate Ali Rahimi received the best Master's thesis award from the Canadian AI Association for 2024! Ali's masters thesis shows that SOTA MBRL methods like Dreamer and MuZero are not adaptive and he also has a fix!

Canadian AI Assoc. / Assoc. canadienne pour l'IA

@c_a_i_a_c

3 months

We are very pleased to announce Ali Rahimi Kalahroudi (Université de Montréal) as the recipient of the CAIAC 2024 Best Master's Thesis Award. Ali's thesis was "Towards Adaptive Deep Model-Based Reinforcement Learning."

1

3

15

3

9

68

Sarath Chandar

@apsarathchandar

7 years

All accepted papers at ICML Lifelong Learning Workshop are now available online: #icml2017

ACCEPTED PAPERS | icml-2017

rlabstraction2016.wixsite.com

0

32

65

Sarath Chandar

@apsarathchandar

7 years

Check our workshop on "Lifelong Learning: A Reinforcement Learning Approach" at ICML2017: #icml2017 #AI

OVERVIEW | icml-2017

rlabstraction2016.wixsite.com

2

17

64

Sarath Chandar

@apsarathchandar

4 years

Happy to announce that the 4th edition of the lifelong learning workshop will happen at #ICML2020 @icmlconf . We ( @shagunsodhani , @ravi_iitm , Doina Precup, and I) are experimenting with a new (or very old?) format for the workshop this year. Stay tuned for more details and CfP!

1

9

62

Sarath Chandar

@apsarathchandar

2 years

Yoshua Bengio talking about generalization beyond the training distribution at @CoLLAs_Conf !

2

14

63

Sarath Chandar

@apsarathchandar

4 years

In this recent interview with @CIFAR_News , I talk about lifelong machine learning, my experience with CIFAR DLRL Summer Schools, and how great is Canada for collaborative research :) Looking forward to the #DLRL panel tomorrow!

CIFAR

@CIFAR_News

4 years

Canada CIFAR AI Chair @apsarathchandar @MilaMontreal builds #MachineLearning systems that learn from new data. He’s joining a #DLRL panel tomorrow on making the jump from student to faculty w Joelle Pineau, @williamleif , Courtney Paquette, @audurand

0

9

24

0

8

59

Sarath Chandar

@apsarathchandar

2 years

@CoLLAs_Conf #CoLLAs2022 was a big success! We had 64 accepted papers, 230+ participants, 8 exciting invited talks! This is a thank you thread for everyone involved: 1/n

1

6

57

Sarath Chandar

@apsarathchandar

2 years

It is time for @icmlconf , @NeurIPSConf , @iclr_conf to go to India as well! imho it is long overdue!

Chhavi Yadav

@chhaviyadav_

2 years

The 14th **Asian Conference on Machine Learning** is coming to India! It will be in a hybrid mode, offline meeting in Hyderabad. Submit your works here! There are both journal (ddl 26th May)and conference (ddl 23 June) tracks.. Check for more details!

1

8

51

1

6

58

Sarath Chandar

@apsarathchandar

3 years

CoLLAs 2022 CFP is out! Highlights: Proceedings in PMLR, revise-resubmit option, 9 pages + an optional 10th page to avoid wasting hours fitting your paper to a strict page limit, appendix in same pdf.

CoLLAs 2025

@CoLLAs_Conf

3 years

Call for Papers is now out! You can find more details about the paper submission and latex style files here:

2

37

169

1

13

54

Sarath Chandar

@apsarathchandar

2 years

Foundation models are pure marketing and unfortunately good marketing always wins. We don’t use it in my group. We just call them as large language models.

Sasha Luccioni, PhD 🦋🌎✨🤗

@SashaMTL

2 years

@deliprao Foundation models are an *invented* concept. Let's not give them more validity, please

2

1

21

4

1

53

Sarath Chandar

@apsarathchandar

6 years

My handwritten notes on Introduction to Machine Learning for the course I taught at McGill University: #MachineLearning

0

8

53

Sarath Chandar

@apsarathchandar

5 years

Congratulation to Chinnadhurai and Sandeep for the nomination for the best paper awards at #ACL2019 !

Do Neural Dialog Systems Use the Conversation History Effectively?...

Neural generative models have been become increasingly popular when building conversational agents. They offer flexibility, can be easily adapted to new domains, and require minimal domain...

arxiv.org

Sarath Chandar

@apsarathchandar

5 years

Attention MAY NOT be all you need. You also need recurrence. Interesting work by Chinnadhurai Sankar and Sandeep Subramanian: #ACL2019

0

21

87

0

13

50

Sarath Chandar

@apsarathchandar

3 years

Lifelong Hanabi is now accepted at ICML 2021! If you want to try your new lifelong learning algorithms in Hanabi, here is the code for the benchmark: #ICML2021 @icmlconf @Mila_Quebec

GitHub - chandar-lab/Lifelong-Hanabi: A Continual Multi-agent RL testbed based on Hanabi

A Continual Multi-agent RL testbed based on Hanabi - chandar-lab/Lifelong-Hanabi

github.com

Sarath Chandar

@apsarathchandar

4 years

Are you tired of manually creating new tasks for Lifelong RL? We introduce Lifelong Hanabi in which every task is coordinating with a partner that's an expert player of Hanabi. Work led by @HadiNekoei and @akileshbadri . paper: @Mila_Quebec 1/n

1

17

85

1

6

47

Sarath Chandar

@apsarathchandar

1 year

Introducing an improved adaptive optimizer: Adam with Critical momenta (Adam+CM)! Unlike traditional Adam, it promotes exploration that paves the way to flatter minima and leads to better generalization. Link to our paper: Work led by: @pranshumalviya8

0

8

46

Sarath Chandar

@apsarathchandar

3 years

I will be teaching a graduate-level Machine Learning course @polymtl / @Mila_Quebec in Fall 2021 - . The course is online. If you are a student in any of the Quebec Universities, you can register for the course here:

Course Info

chandar-lab.github.io

1

8

45

Sarath Chandar

@apsarathchandar

8 years

My first shared notes on Sequence-to-Sequence Learning as Beam-Search Optimization: #deeplearning #NLProc

1

15

47

Sarath Chandar

@apsarathchandar

3 years

We are very excited to release RLHive (), an RL research framework in PyTorch. RLHive supports both single-agent and multi-agent RL! This is an outcome of a year-long effort by @dapatil211 , @HadiNekoei , @alirkay , @saikrishna_gvs .

GitHub - chandar-lab/RLHive

Contribute to chandar-lab/RLHive development by creating an account on GitHub.

github.com

Darshan Patil

@dapatil211

3 years

After several months of hard work, I am proud to share the release of RLHive, a research framework for RL in PyTorch for both Single Agent and Multi Agent use cases. Github: Docs+Tutorials: 1/n

6

40

192

0

6

41

Sarath Chandar

@apsarathchandar

6 months

The Computer and Software Engineering Dept. at Polytechnique Montreal is hiring for a tenure-track faculty position in Trustworthy AI! Eligible candidates will be nominated to become affiliated with @Mila_Quebec ! Link to the official call in the next tweet! Deadline: 8 April

1

21

36

Sarath Chandar

@apsarathchandar

4 years

If you are interested in lifelong learning / continual learning, please check this thread for the amazing list of speakers and panellists at our 4th Lifelong Learning workshop @icmlconf this Saturday! You can ask your questions to the panellists here:

Shagun Sodhani

@shagunsodhani

4 years

Highlights of the upcoming 4th #Lifelong ML workshop @icmlconf on Sat, July 18 A stellar panel discussion with Doinna Precup ( @DeepMind ), Eric Eaton (UPenn), @irinarish ( @MILAMontreal ), @harmvanseijen ( @MSFTResearch ) & Martha White ( @AmiiThinks ) Ask Q at

1

8

46

2

8

39

Sarath Chandar

@apsarathchandar

7 years

Slides for our memory augmented neural networks tutorial at #emnlp2017 are now available online:

MANN for NLP @ EMNLP 2017

When? 8 Sep 2017, Afternoon Where? EMNLP 2017 Slides: click here. Description: Designing of general-purpose learning algorithms is a long-standing goal of artificial intelligence. A general purpose...

sites.google.com

1

6

39

Sarath Chandar

@apsarathchandar

3 years

Our lab has its own Twitter handle now! Managed by the awesome students :) Please follow us to hear more about our new research projects. We will also tweet about the works of others that we are excited about!

Chandar Lab

@ChandarLab

3 years

Hello World! We are finally on Twitter! @ChandarLab is a research group based in @polymtl and @Mila_Quebec led by @apsarathchandar . Our work focuses on #LifelongLearning , #DeepLearning , #ReinforcementLearning , and #NLProc . Follow us for the latest news on our work!

0

15

54

1

0

37

Sarath Chandar

@apsarathchandar

1 year

If you wanna learn more about the recent advances in deep learning, reinforcement learning, and NLP that has come out of my lab in the past year, consider attending our lab's annual research symposium on Aug 8 and 9: You can join remotely too!

1

9

36

Sarath Chandar

@apsarathchandar

9 months

Translation of this thread: “I have no clue/expertise about general purpose ML systems. But here is my authoritative opinion on how to evaluate them.”

@[email protected] on Mastodon

@emilymbender

9 months

Reflecting on this a bit further -- I think this episode really emblematic of how broken evaluation is in our field right now. In general, data work is important, and creating benchmarks is work that has been historically undervalued. However:

10

22

171

6

2

37

Sarath Chandar

@apsarathchandar

2 years

Want to know more about what is happening at @ChandarLab ? Please join our annual research symposium () virtually or in person (Montreal) this August 11! You will hear my students talking about lifelong learning, reinforcement learning, NLP, and DL!

1

6

37

Sarath Chandar

@apsarathchandar

6 years

New preprint: On Training RNNs for Lifelong Learning. Joint work with @shagunsodhani and Yoshua Bengio. Will be presented at Continual Learning workshop @NipsConference #NeurIPS2018

Towards Training Recurrent Neural Networks for Lifelong Learning

Catastrophic forgetting and capacity saturation are the central challenges of any parametric lifelong learning system. In this work, we study these challenges in the context of sequential...

arxiv.org

0

5

36

Sarath Chandar

@apsarathchandar

5 months

Unfortunately, Hinton is wrong. Open sourcing is better than only a handful of corporate companies owning them.

Tolga Bilge

@TolgaBilge_

5 months

Geoffrey Hinton is right. So-called open sourcing of the biggest models is completely crazy. As AI models become more capable they should become increasingly useful in bioweapons production and for use in large-scale cyber attacks that could cripple critical infrastructure.

77

23

141

2

3

36

Sarath Chandar

@apsarathchandar

2 years

The first edition of the Conference on Lifelong Learning Agents ( @CoLLAs_Conf ) will happen in hybrid mode in Montreal from Aug 22 - Aug 24! Registration for virtual and in-person attendance is now open! .

1

12

35

Sarath Chandar

@apsarathchandar

3 years

My department at @polymtl is hiring a tenure-track professor in computer and software engineering. Strong ML candidates can get @Mila_Quebec affiliation. If you are working at the intersection of Systems and ML, we are looking for you! Deadline: April 05.

0

11

34

Sarath Chandar

@apsarathchandar

5 years

I enjoyed every second of this talk! I highly recommend it!

Shimon Whiteson

@shimon8282

5 years

Video of my talk on Bayes-adaptive RL at the NeurIPS Deep RL Workshop is here (starting at 1:05):

1

49

211

0

3

33

Sarath Chandar

@apsarathchandar

2 years

@yoshitomo_cs Perhaps you should also mention which paper is this :)

1

0

32

Sarath Chandar

@apsarathchandar

5 years

@polymtl @MILAMontreal Thanks to my advisers and mentors: Yoshua Bengio, @hugo_larochelle , Balaraman Ravindran, Mitesh Khapra, Gerry Tesauro, @caglarml , Susan Elias! 2/2

1

0

32

Sarath Chandar

@apsarathchandar

4 years

Check out our recent work on #DrugDiscovery by learning to navigate the synthetically accessible chemical space using Reinforcement Learning ( #RL ) ---. Led by @saikrishna_gvs and @boris_luv of .

Learning To Navigate The Synthetically Accessible Chemical Space...

Over the last decade, there has been significant progress in the field of machine learning for de novo drug design, particularly in deep generative models. However, current generative approaches...

arxiv.org

0

5

32

Sarath Chandar

@apsarathchandar

2 years

Final keynote talk @CoLLAs_Conf by @RichardSSutton !

1

4

33

Sarath Chandar

@apsarathchandar

9 months

Are you annoyed by random reviews in mega conferences? You should consider switching to small but focused venues like @CoLLAs_Conf , @LogConference , @Conf_CLeaR , @automl_conf for quality feedback!

CoLLAs 2025

@CoLLAs_Conf

9 months

Do you work in lifelong/continual/meta/in-context/transfer/multi-task/few-shot/zero-shot/curriculum/OOD/active/online learning paradigms in ML/RL? CoLLAs is the premier venue for these topics! Submit your best work to CoLLAs 2024! Deadline: 15 Feb 2024 #CoLLAs2024 @CoLLAs_Conf

1

14

55

0

6

33

Sarath Chandar

@apsarathchandar

4 years

Call for papers for the Lifelong Learning Workshop @icmlconf is out - . The workshop will be virtual this year! #ICML2020

Lifelong ML

Write an awesome description for your new site here. You can edit this line in _config.yml. It will appear in your document head meta (for Google search results) and in your feed.xml site description.

lifelongml.github.io

Sarath Chandar

@apsarathchandar

4 years

Happy to announce that the 4th edition of the lifelong learning workshop will happen at #ICML2020 @icmlconf . We ( @shagunsodhani , @ravi_iitm , Doina Precup, and I) are experimenting with a new (or very old?) format for the workshop this year. Stay tuned for more details and CfP!

1

9

62

0

8

32

Sarath Chandar

@apsarathchandar

2 years

This is a great list of 64 interesting papers focusing on lifelong learning, meta learning, few shot learning, transfer learning, reinforcement learning! Please do check the papers and their video presentations! @CoLLAs_Conf

CoLLAs 2025

@CoLLAs_Conf

2 years

You can find all the 64 accepted papers (pdf) @CoLLAs_Conf #CoLLAs2022 and their video presentations here: . You can watch these video presentations even if you have not registered to attend the conference!

0

33

88

0

9

32

Sarath Chandar

@apsarathchandar

4 years

PhD thesis topics suggested by Partha Talukdar at the #ICML2020 Lifelong Learning workshop!

Shagun Sodhani

@shagunsodhani

4 years

Partha also shared a list of interesting problems and PhD thesis topics in Never Ending Learning and #Lifelong Learning

0

2

11

0

5

32

Sarath Chandar

@apsarathchandar

4 years

Of course a sad day in history! It is important to commit to make education and research opportunities more equitable. To that, I will keep open exclusive internship positions for 2 undergraduate #WomenInAI every year starting Summer '21 at #ChandarLab @Mila_Quebec @polymtl .

Polytechnique Mtl

@polymtl

4 years

Six décembre 2020 – 31 ans après - Souvenir et recueillement

1

74

209

0

4

29

Sarath Chandar

@apsarathchandar

2 years

Frustration after staying in a few hotels for a vacation - all North American 4-star hotels should go learn about hospitality and customer service from Indian 4-star hotels. Indian hotels provide 50X better service for 5X lower price.

1

29

Sarath Chandar

@apsarathchandar

4 years

Probing the representations of generative dialogue models shows interesting trends. We observe that probing tasks can holistically evaluate generative dialogue models. The full paper can be found here ! Work led by @prasannapartha . #NLProc 1/5

1

4

27

Sarath Chandar

@apsarathchandar

4 years

Lecture #6 of the Machine Learning course is now available in the playlist: . This lecture discusses about empirical risk minimization, bias-variance trade-off, and different approaches for classification. #MachineLearning

Machine Learning

An introductory course in machine learning by Prof. Sarath Chandar. Please check http://sarathchandar.in/teaching/ml/fall2020/ for the full course and the sc...

www.youtube.com

0

2

26

Sarath Chandar

@apsarathchandar

1 year

If you have a recent @TmlrOrg paper on lifelong/continual/multi-task/meta/transfer/online/active/ood learning, consider presenting the paper as a poster at @CoLLAs_Conf and get a CoLLAs certification by TMLR! I’m very excited about this collaboration with @TmlrOrg !

CoLLAs 2025

@CoLLAs_Conf

1 year

We are excited to announce a new "Journal Track" at CoLLAs 2023! This track gives an opportunity for recently published journal papers (that are aligned with the theme of CoLLAs) to be presented as posters at CoLLAs! Details here: 1/n

1

5

33

0

8

27

Sarath Chandar

@apsarathchandar

4 years

Lecture #4 of the Machine Learning course is now available in the playlist: . The first part introduces statistical decision theory and the second part covers basis function regression models and geometric view of linear regression. #MachineLearning

Machine Learning

An introductory course in machine learning by Prof. Sarath Chandar. Please check http://sarathchandar.in/teaching/ml/fall2020/ for the full course and the sc...

www.youtube.com

0

16

25

Sarath Chandar

@apsarathchandar

4 years

Check out our recent work on a new experimental setup and metric for evaluating model-based #RL methods. Work led by @harmvanseijen (Microsoft Research) and my amazing interns @HadiNekoei and @evanracah .

Harm van Seijen

@harmvanseijen

4 years

We introduce a new experimental setup and metric for evaluating model-based RL methods. The metric measures how quickly an RL methods adapts to local changes in the environment.

1

9

46

0

8

26

Sarath Chandar

@apsarathchandar

9 months

Jana was the first postdoc @ChandarLab and I’m extremely proud that he is starting his own lab @DalhousieU ! Jana is a great researcher, excellent mentor, and he truly cares about training students to do impactful research! I strongly encourage students to apply to his lab!

Janarthanan Rajendran

@rj_janarthanan

9 months

Pleased to share that I will be joining @DalhousieU as an Assistant Professor in Jan '24. :) I have openings for Master’s & PhD positions in Deep Reinforcement Learning. Details: . Please share with potential candidates and within your network. Thanks!

4

16

62

2

1

26

Sarath Chandar

@apsarathchandar

6 months

I am extremely proud of this work by my amazing students @M_R_Samsami and @artemZholus along with @rj_janarthanan (prev. my postdoc, now professor @DalhousieU ). @M_R_Samsami is finishing his masters and is in job market! He is a great catch if you are looking to hire!

Sarath Chandar

@apsarathchandar

6 months

🎉 Excited to announce our work "Recall to Imagine (R2I)" got an oral spot at #ICLR2024 ! R2I is a generalist and computationally efficient agent that shines in RL memory tasks, showing superhuman performance in most complex memory tasks. Kudos to @M_R_Samsami & @artemZholus ! 1/n

4

20

116

3

4

25

Sarath Chandar

@apsarathchandar

4 years

Lecture #3 of the Machine Learning course is now available in the playlist: . In this lecture, we discuss ways to avoid overfitting, basic ML pipeline, and K-NN for classification. #MachineLearning

Machine Learning

An introductory course in machine learning by Prof. Sarath Chandar. Please check http://sarathchandar.in/teaching/ml/fall2020/ for the full course and the sc...

www.youtube.com

0

6

25

Sarath Chandar

@apsarathchandar

1 year

Why should we consider GPT-4 as state of the art in research? It’s a black box product. OpenAI and Microsoft can write papers on GPT-4 because they are selling the product. We should be using only open source LLM models for research.

4

0

26

Sarath Chandar

@apsarathchandar

9 months

CoLLAs is the community of researchers who truly care about the continual learning problem! If you work in any non-IID / non-stationary learning setting, CoLLAs will be your home conference! Consider joining us for CoLLAs 2024!

CoLLAs 2025

@CoLLAs_Conf

9 months

Do you work in lifelong/continual/meta/in-context/transfer/multi-task/few-shot/zero-shot/curriculum/OOD/active/online learning paradigms in ML/RL? CoLLAs is the premier venue for these topics! Submit your best work to CoLLAs 2024! Deadline: 15 Feb 2024 #CoLLAs2024 @CoLLAs_Conf

1

14

55

0

6

25

Sarath Chandar

@apsarathchandar

1 year

If you wanna learn about the whole landscape of efficient Transformers, I highly recommend this excellent suvery on faster and lighter Transformers by my postdoc Quentin Fournier: (Accepted in ACM Computer Surveys)

A Practical Survey on Faster and Lighter Transformers

Recurrent neural networks are effective models to process sequences. However, they are unable to learn long-term dependencies because of their inherent sequential nature. As a solution, Vaswani et...

arxiv.org

0

4

25

Sarath Chandar

@apsarathchandar

2 years

Panel discussion on the effects of scaling in lifelong learning @CoLLAs_Conf !

1

4

23

Sarath Chandar

@apsarathchandar

2 years

Canada is looking for talented immigrants and you can get your PR in a year and citizenship in less than 5 years (outside Quebec). These H1B visa holders should just consider moving to Toronto :)

Dare Obasanjo🐀

@Carnage4Life

2 years

Stories below of Indian H-1B visa holders jumping from big tech (Google & Apple) to startups (Coinbase & Peloton), getting laid off then having to leave the country because they couldn’t find jobs in 60 days are harrowing. It’s why H-1Bs end up feeling like indentured servants.

123

522

3K

1

0

24

Sarath Chandar

@apsarathchandar

8 years

Dynamic Neural Turing Machine with Soft and Hard Addressing Schemes:

1

3

23

Sarath Chandar

@apsarathchandar

3 years

Only one week left for the application deadline! In addition to the listed topics (memory augmented networks, learning through language interaction, optimization, lifelong learning, RL), I am also looking for MSc/PhD students to work in the intersection of ML and Drug Discovery.

Sarath Chandar

@apsarathchandar

3 years

I have multiple open MSc/PhD positions on memory augmented neural nets, RL, Lifelong Learning, NLP for Fall 2022 at @ChandarLab / @Mila_Quebec / @polymtl ! Details: Applications due Dec 1st:

4

46

182

1

4

23

Sarath Chandar

@apsarathchandar

10 months

Can large language models consolidate world knowledge? The answer turns out to be "NO". I am very excited to present to you our @emnlpmeeting 2023 paper (main track) which studies this important limitation of LLMs. Work led by my amazing PhD student @GabrielePrato !

Gabriele Prato

@GabrielePrato

11 months

The ability to combine information from different training documents is crucial for many applications. We introduce the first study on the knowledge consolidation capabilities of LLMs:

1

3

19

0

5

23

Sarath Chandar

@apsarathchandar

9 months

I will be at NeurIPS from 14-17 Dec. I will be recruiting a postdoc in Reinforcement Learning. Please email me to meet during the conference if you are looking for a postdoc position starting soon! #NeurIPS2023

0

5

23

Sarath Chandar

@apsarathchandar

2 years

I wasted my time reading this article. Even a first year phd student would have the same vision. What is so special to write an article about a trivial vision which is not even published in arxiv yet? This fan following must stop. Doing PR even before the preprint is next level!

Patrick Krauss

@Krauss_PK

2 years

Wow! AGI finally solved! 😂 @ylecun discovers what's missing so far in deep learning: common sense and a world model! @GaryMarcus @maier_ak

6

45

2

23

Sarath Chandar

@apsarathchandar

1 year

I have been saying this for a few years now!

Andrew Gordon Wilson

@andrewgwils

1 year

We should have a major machine learning conference (NeurIPS, ICML, ICLR, etc.) in India.

14

67

577

1

0

23

Sarath Chandar

@apsarathchandar

4 years

Lecture #2 of the Machine Learning course is available now! In this lecture, we discuss regression and overfitting.

Machine Learning - Lecture 02

An introductory course in machine learning by Prof. Sarath Chandar.Please check http://sarathchandar.in/teaching/ml/fall2020/ for the full course and the sch...

www.youtube.com

0

4

22

Sarath Chandar

@apsarathchandar

4 years

Please check out our recent preprint on maximum reward formulation in #RL : . This work improves upon our #ICML2020 paper on RL for drug discovery (). Work led by @saikrishna_gvs .

Learning To Navigate The Synthetically Accessible Chemical Space...

Over the last decade, there has been significant progress in the field of machine learning for de novo drug design, particularly in deep generative models. However, current generative approaches...

arxiv.org

0

4

21

Sarath Chandar

@apsarathchandar

4 years

A recent interview about our ongoing efforts on RL for drug discovery. Led by @saikrishna_gvs and @boris_luv of . Accepted at @icmlconf . The preprint can be found here: .

Learning To Navigate The Synthetically Accessible Chemical Space...

Over the last decade, there has been significant progress in the field of machine learning for de novo drug design, particularly in deep generative models. However, current generative approaches...

arxiv.org

CIFAR

@CIFAR_News

4 years

Canada CIFAR AI Chair @apsarathchandar of @polymtl @MILAMontreal is using a CIFAR #AI & #COVID -19 Catalyst Grant to find new ways to use #ReinforcementLearning to speed drug discovery pathways: story by @JosephElfassi in @CSCIENCEIA (in French)

0

5

10

0

7

22

Sarath Chandar

@apsarathchandar

2 years

Can’t agree more! There is no good reason why a paper with Stanford-only author list gets all citations for the hard work of other research groups! Most people hate the name for this marketing only.

Soumith Chintala

@soumithchintala

2 years

@chrmanning @tdietterich @roydanroy @karpathy @ylecun @percyliang @RishiBommasani The jazz analogy is quite good from a credit assignment view. Very deeply, i think the disagreements are around other academics thinking "why do you get citations, credit and eventually prizes for consolidating other people's breakthroughs and putting a catchy term around it".

5

1

33

1

0

22

Sarath Chandar

@apsarathchandar

3 years

Any good resources to develop intuitions about linear algebra concepts? Please post your suggestions in this thread :)

Darshan Patil

@dapatil211

3 years

I feel like most courses/textbooks focus on the mechanical aspects of linear algebra. Anyone know of any resources to develop good intuitions about concepts?

5

0

11

8

2

22

Sarath Chandar

@apsarathchandar

2 years

It takes less than a year to get PR in Canada (except Quebec). Indians in America should consider immigrating to Canada! Unlike America, Canada is actually more welcoming for highly skilled immigrants!

rohan anil

@_arohan_

2 years

Someone please approve the greencards from the backlog please 🫡

1

0

19

0

22

Sarath Chandar

@apsarathchandar

8 years

Check out details about our tutorial on multilingual multimodal language processing using neural networks #naacl2016

NAACL HLT 2016 | San Diego, CA

The 15th Annual Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies will be held in San Diego, California, June 12 to June 17, 2016....

naacl.org

0

6

20

Sarath Chandar

@apsarathchandar

7 years

Chelsea Finn talks about lifelong few shot learning at #lifelonglearning workshop #icml2017

1

3

21

Sarath Chandar

@apsarathchandar

2 years

The origin of multi-task learning - Rich Caruana @CoLLAs_Conf

1

3

21

Sarath Chandar

@apsarathchandar

1 year

Conference proceedings are equally junk and we can’t keep up with them too. Research is a noisy process and a researcher should be able to separate the signal from the noise. Peer review was never perfect and will never be perfect. Arxiv does more good than bad!

@[email protected] on Mastodon

@emilymbender

1 year

@tdietterich @TaliaRinger @mmitchell_ai @ErikWhiting4 @arxiv arXiv is a cancer that promotes the dissemination of junk "science" in a format that is indistinguishable from real publications. And promotes the hectic "can't keep up" + "anything older than 6 months is irrelevant" CS culture. >>

18

9

71

1

0

21

Sarath Chandar

@apsarathchandar

5 months

I’m extremely proud of my student @Megh1211 who has been awarded the Antidote scholarship for NLP! I received the Antidote scholarship during my phd at @UMontrealDIRO and @Mila_Quebec and very happy to see my student joining the list of recipients! 😃

Mila - Institut québécois d'IA

@Mila_Quebec

5 months

🎉 Congratulations to Megh Vipul Thakkar, a Master's student (Polytechnique/Mila) who has been awarded the eight Antidote Scholarship from @druide_info in Natural Language Processing (NLP), worth $20,000. Congratulations!

1

4

27

0

21

Sarath Chandar

@apsarathchandar

4 months

Quality of reviews are already too bad in ML conferences! We should not invite inexperienced and new researchers to start reviewing. They need more experience doing research before starting to review others works.

Rosanne Liu

@savvyRL

4 months

I'm happy to nominate new reviewers for #NeurIPS . If you are interested, send me your email, OpenReview profile, and a short blurb about your research background and reviewing experience — inexperienced/new researchers are welcome too!

8

10

145

3

1

20

Sarath Chandar

@apsarathchandar

2 years

Every ethnicity has cheating and non-cheating members. Most asians I have seen are sincere, hard-working, smarter, talented. I think part of the reason for this prejudice is just the insecurity of non-asians who make such comments!

Chenyan Xiong

@XiongChenyan

2 years

@thegautamkamath Yes. Very sadly. I have been told directly in person that Asian tend to cheat, etc. multiple times. I fought back every single time. But that is also because I have certain privilege's that enabled me to do so, can't image how bad it is for those without that.

0

12

0

1

19