Gilles Louppe @glouppe Twitter profile

Pinned Tweet

Gilles Louppe

1 month

Very excited to finally share the excellent work of my PhD students @RochmanOmer and @SachaLewin on NeuralMPM, a neural emulation framework for particle-based simulations!

3

24

116

Last Seen Profiles

@SUSILKUMARDHAR1

@Death2537

@AnAL_faNs_page

@Marcobrave1

@cegiljayke

@TSNSteveLloyd

@SemClubismo_FC

@sophierauszer

@CharlesHol42379

@OrdinalSeiyans

@DavidCRicardo

@fivesion

@Nagumogumogu_24

@Phil30326124754

@abdullahsaljab1

@Division1Soccer

@finbirds

@boomer78alive

@phoaloughd9741

@Lauren_Whrtn

@NimahGobir

@Jackie_Xo_

@Cee_jay29

@doremifaso64

@ItsChipJones

@naomiiuui

@Extreme___DEO

@JadonHickman

@BAKIAKKKK

@StaceyJSpiehler

@DollyPartoner

@yattareli

@virginiamaestro

@Health93104487

@SouthwarkLS

@erikjasperkier

Gilles Louppe

@glouppe

4 years

OpenAI's CLIP is confused by Belgian art 🤷‍♂️

61

941

5K

Gilles Louppe

@glouppe

6 years

In Belgium, scientific papers that originate from public funds can now all be made public in open access, regardless of any contract with publishers. It is written in the law. And retroactive.

Paul Thirion

@PaulThir

6 years

Voilà, la loi fédérale belge autorisant #OAGreen publiée aujourd'hui au Moniteur belge art. 29 page 68691 TOUS articles scientif des chercheurs belges peuvent désormais être déposés en #OA sur #RI avec embargo max 6/12 mois. Quel que soit contrat signé !

4

62

77

29

988

2K

Gilles Louppe

@glouppe

2 years

Excited to kick off the second term with my students! Time to teach Deep Learning again! This year, I have decided to say goodbye to RNNs and GANs and cover GNNs and score-based diffusion models instead 🤖💡

19

210

1K

Gilles Louppe

@glouppe

2 years

Bayesian nugget of the day: Metropolis-Hastings. 1) Draw a candidate θ from a proposal q(θ|θₜ), 2) Accept θ if u < π(θ)/π(θₜ) q(θₜ|θ)/q(θ|θₜ) for u~U[0,1], 3) Repeat. Beautifully, this results in a Markov chain whose stationary distribution coincides with the target π!

10

115

635

Gilles Louppe

@glouppe

3 years

Finally done with teaching my Deep Learning class for this term! This year's version includes new lectures on autodiff and transformers. All (787) slides can be found at 🧑‍🎓

lec-all.pdf

drive.google.com

6

95

450

Gilles Louppe

@glouppe

6 years

Scientific and societal impact of research comes rarely from where we expect. Open source software is one such example: today, Scikit-Learn just passed 10000 citations! Congratulations to all contributors for all the progress they triggered!

5

123

443

Gilles Louppe

@glouppe

6 years

Remember the Galton board? When nails are positioned such that the probability of bouncing left is always the same, the resulting distribution is a binomial, for which the likelihood p(x) of bin x is known analytically.

3

99

392

Gilles Louppe

@glouppe

3 years

Today I used @OpenAI Davinci model (GPT-3) for an actual Turing test in my first lecture of Introduction to AI. It turned out great! Davinci passed the test! 🤖

3

27

311

Gilles Louppe

@glouppe

7 years

Tomorrow I'll actually teach my first ever lecture on deep learning, rebuilding all the basic constructs, starting from LDA up to deep rectified networks. Lecture slides available at

10

78

304

Gilles Louppe

@glouppe

4 years

When your colleagues and friends send a welcome card to celebrate your newborn using the #NeurIPS2020 paper template ❤️ Thanks all! See you soon :)

12

291

Gilles Louppe

@glouppe

7 years

It's out! Our latest paper with @KyleCranmer : Adversarial Variational Optimization of Non-Differentiable Simulators

6

91

252

Gilles Louppe

@glouppe

2 months

Watching PhD students lose their last crumbs of illusion about science when faced with stubborn, unreasonable, or completely absent reviewers is heartbreaking. We've got to do better as a community. #NeurIPS2024

6

24

262

Gilles Louppe

@glouppe

2 years

Started training my baby, hand-made 40M GPT model on Harry Potter books 🤓 GPUs go brrrr! 🚀 ( @PyTorch 's nn.DataParallel makes multi-GPU support so easy <3)

9

19

235

Gilles Louppe

@glouppe

5 years

New paper by my student @WehenkelAntoine : Unconstrained Monotonic Neural Networks! In this work, we show how to make use of free-form neural networks to model arbitrary monotonic functions and derive a new autoregressive flow.

2

67

225

Gilles Louppe

@glouppe

6 years

Brilliant step-by-step review of optimization methods for large-scale machine learning, by Léon Bottou et al. Must read if you want to understand why SGD is actually a good optimization algorithm in ML!

Optimization Methods for Large-Scale Machine Learning | SIAM Review

This paper provides a review and commentary on the past, present, and future of numerical optimization algorithms in the context of machine learning applications. Through case studies on text...

epubs.siam.org

1

74

228

Gilles Louppe

@glouppe

7 years

The Kalman Filter, as implemented in assembler in the Apollo Guidance Computer! Those little things you discover when preparing your next lecture on temporal models...

2

76

222

Gilles Louppe

@glouppe

4 years

Who knew? Changing the reset gate in @kchonyc 's GRU so that the gate can take values in ]0,2[ instead of ]0,1[ makes the cell bistable, hence enabling long-lasting memories! Very nice work by my colleagues @vecovennicolas , @DamienERNST1 and Guillaume Drion!

Damien ERNST

@DamienERNST1

4 years

We have taken inspiration from biological neuron bistability to embed Recurrent Neural Nets (RNN) with long-lasting memory at the cellular level. Excellent performances on time-series which require very long memory. #DeepLearning #ArticialIntelligence

2

51

228

2

53

221

Gilles Louppe

@glouppe

2 years

The more I talk about simulation-based inference, the more I realize that the concept of an intractable likelihood is completely foreign in some fields. A short thread 🧵

3

39

220

Gilles Louppe

@glouppe

1 year

Had quite some fun this morning teaching a new lecture on #GNNs ! 🧑‍🏫 Key takeaway: GNNs are built on the blueprint of stacking shared, local, and permutation invariant functions. They generalize classic architectures like convnets & transformers to graph-structured data 🤯🌐

3

40

208

Gilles Louppe

@glouppe

4 years

📢 My research group has an open position for a PhD candidate in deep-learning for simulation-based inference. Details available at PM for further details 🤖🔭

1

70

185

Gilles Louppe

@glouppe

4 years

You say Normalizing Flows? We see Bayesian Networks! Quite excited to announce two papers @WehenkelAntoine and I have just released on arXiv! + Thread below 👇

Graphical Normalizing Flows

Normalizing flows model complex probability distributions by combining a base distribution with a series of bijective neural networks. State-of-the-art architectures rely on coupling and...

arxiv.org

Antoine Wehenkel

@WehenkelAntoine

4 years

I am VERY excited to share not 1 but 2 papers hot from arxiv, joint work with @glouppe !🥳 We are showing strong connections between Bayesian networks and normalizing flows. 1)Using Bayesian networks to better understand NFs and 2)increasing BN framework with the NF machinery.

4

17

97

1

36

176

Gilles Louppe

@glouppe

2 years

Bayesian recipe of the day 🧑‍🍳: Take a simple latent variable model where the latents are Gaussian and the observed variables are linear Gaussian. Fit the linear projection parameters by maximum likelihood estimation. Then, posterior inference gives you (Probabilistic) PCA! 🤯

3

16

172

Gilles Louppe

@glouppe

4 years

Finally found some time for hacking around with JAX! It feels almost as if I was back in 2011, writing Numpy code for sklearn, except now it is fully differentiable and runs on GPUs 🤓

2

8

166

Gilles Louppe

@glouppe

1 year

The materials of my lectures on i) deep generative models (VAEs, diffusion models, flows) and ii) simulation-based inference can now all be found at

GitHub - glouppe/ssi2023

Contribute to glouppe/ssi2023 development by creating an account on GitHub.

github.com

Gilles Louppe

@glouppe

1 year

On my way to SFO ✈️ for a week at the 51st @SLAClab summer institute Ping me for ☕ around SLAC or Stanford

0

2

22

1

39

163

Gilles Louppe

@glouppe

3 years

Variable importances computed from random forests are Shapley values! Happy to share an 8-year follow-up to my very first #NeurIPS paper, back in 2013. [accepted at #NeurIPS2021 ] 🧵

From global to local MDI variable importances for random forests...

Random forests have been widely used for their ability to provide so-called importance measures, which give insight at a global (per dataset) level on the relevance of input variables to predict a...

arxiv.org

7

31

160

Gilles Louppe

@glouppe

7 years

A million-agent RL experiment that reveals population dynamics following population-prey equations! Super nice

A Study of AI Population Dynamics with Million-agent Reinforcement Learning

We conduct an empirical study on discovering the ordered collective dynamics obtained by a population of intelligence agents, driven by million-agent reinforcement learning. Our intention is to...

arxiv.org

4

61

146

Gilles Louppe

@glouppe

8 years

Bayesian optimisation for tuning scikit-learn hyper-parameters Feedback welcome before the 1st release of `skopt`

10

56

145

Gilles Louppe

@glouppe

7 years

My #PyData Amsterdam talk on Bayesian Optimization with Scikit-Optimize is at Thanks @gabriele_modena for chairing!

PyData 2017: Bayesian optimization with Scikit-Optimize

Bayesian optimization with Scikit-Optimize Gilles Louppe @glouppe PyData Amsterdam 2017

docs.google.com

1

46

131

Gilles Louppe

@glouppe

7 years

Always knew ResNets looked awfully similar to boosting! Huang, Ash, Langford and Schapire have now demonstrated it

Learning Deep ResNet Blocks Sequentially using Boosting Theory

Deep neural networks are known to be difficult to train due to the instability of back-propagation. A deep \emph{residual network} (ResNet) with identity loops remedies this by stabilizing...

arxiv.org

0

50

131

Gilles Louppe

@glouppe

10 years

A manual for tree huggers: My PhD thesis "Understanding Random Forests: From Theory to Practice" http://t.co/i0JlGOB11W

9

62

128

Gilles Louppe

@glouppe

1 year

Diffusion models are not only good at generating pretty pictures, they can also solve (very) high-dimensional inference problems! Really proud of this last piece of work led by @FrancoisRozet on Bayesian data assimilation 🌍🤖 (We scale to 128x64x64-dimensional posteriors!)

François Rozet

@FrancoisRozet

1 year

📢 Tired of inaccurate weather forecasts? Of course you are, and that's why @glouppe and I are thrilled to announce Score-based Data Assimilation, a novel trajectory inference method powered by score-based generative models. 🧵

5

29

109

1

25

128

Gilles Louppe

@glouppe

6 years

Today is the first lecture of my new Deep Learning course at @UniversiteLiege . We will start easy with some reminders on the fundamentals of machine learning. Materials will be posted every week at Feedback is welcome!

3

23

121

Gilles Louppe

@glouppe

8 years

MinPy, or how to run your Numpy code on a GPU by changing a single import line Also curious to try its autograd

1

55

119

Gilles Louppe

@glouppe

5 years

Do you know of anyone who reproduced the double-U generalization curve of over-parameterized networks? Looking for a friend :-)

9

31

118

Gilles Louppe

@glouppe

11 months

The list of all 191 papers accepted at the #ML4PS2023 NeurIPS workshop is now available at Congratulations to all authors and huge thanks to all reviewers! This year, we reached an unprecedented number of 3.9 reviews per paper on average!

1

17

114

Gilles Louppe

@glouppe

4 years

When code you wrote appears on television🤓CC: @scikit_learn @ogrisel @GaelVaroquaux @amuellerml

zhi

@zhipan01

4 years

THIS KDRAMA JUST IMPORTED SKLEARN

3

24

152

1

5

110

Gilles Louppe

@glouppe

6 years

Phew! I am now halfway through my deep learning lectures. Today we went over recurrent networks, starting from Elman networks up to Differentiable Neural Computers. Slides available et

1

23

107

Gilles Louppe

@glouppe

6 years

At the Isaac Newton institute for mathematics for a few days. Where you find black boards in the bathroom. You cannot be too cautious in case of emergency.

3

6

107

Gilles Louppe

@glouppe

4 years

Lazy tweet: I am looking for applications of automatic differentiation beyond neural nets. Any exciting example I could show to my students? Thinking about things like differentiating through simulations or gradient-based hyper-parameter optimization

42

13

107

Gilles Louppe

@glouppe

2 years

In previous work, we showed that algorithms for simulation-based inference can all produce underdispersed posteriors, which can make them unreliable for scientific inquiry. Today, we are happy to announce a first algorithm for reliable simulation-based inference! 🧵

Stat.ML Papers

@StatMLPapers

2 years

Towards Reliable Simulation-Based Inference with Balanced Neural Ratio Estimation. (arXiv:2208.13624v1 [])

0

5

23

2

20

102

Gilles Louppe

@glouppe

2 years

On behalf of the organizers, I am happy to announce that the Call for Papers is now out! Deadline: September 22. ✍️ #ML4PS2022

Kyle Cranmer

@KyleCranmer

2 years

Great news, our Machine Learning and the Physical Sciences workshop at #NeurIPS2022 was accepted! This will be the fifth edition of this fantastic workshop series. More details to follow. #ML4PS2022

7

85

522

1

23

97

Gilles Louppe

@glouppe

7 years

Nice little gem in today's arXiv: rediscovering Maxwell equations with symbolic search in theory space

TheoSea: Marching Theory to Light

There is sufficient information in the far-field of a radiating dipole antenna to rediscover the Maxwell Equations and the wave equations of light, including the speed of light $c.$ TheoSea is a...

arxiv.org

2

43

92

Gilles Louppe

@glouppe

8 years

Recommendation letter for John Nash. Short and precise.

1

53

89

Gilles Louppe

@glouppe

6 years

This year, I am really satisfied with the second version of my Introduction to AI lectures. Tomorrow will already be the last lecture! All (700+!) slides can be downloaded at

0

27

90

Gilles Louppe

@glouppe

4 years

Happy to announce our latest work led by @ArnaudDelaunoy for fast posterior inference on gravitational wave data using likelihood-to-evidence ratio estimation (AALR / SNRE), reducing inference time from days to minutes or less! 🔭🤖

4

18

91

Gilles Louppe

@glouppe

6 years

Digging into old papers to prepare a deep learning talk for a general audience. I never realized the neocognitron paper also came with an attention model!

2

28

88

Gilles Louppe

@glouppe

2 years

@MFarooq52968219 Materials are available at . Lectures are given in class only

GitHub - glouppe/info8010-deep-learning: Lectures for INFO8010 Deep Learning, ULiège

Lectures for INFO8010 Deep Learning, ULiège. Contribute to glouppe/info8010-deep-learning development by creating an account on GitHub.

github.com

5

22

89

Gilles Louppe

@glouppe

8 years

The boosting strikes back! "AdaGAN: boosting generative models"

AdaGAN: Boosting Generative Models

Generative Adversarial Networks (GAN) (Goodfellow et al., 2014) are an effective method for training generative models of complex data such as natural images. However, they are notoriously hard to...

arxiv.org

0

43

88

Gilles Louppe

@glouppe

4 years

Look what I found in the office! Yesterday, I gave my AI class on top of the very first two volumes of the #NeurIPS proceedings (1987, 1988). Stand on the shoulders of giants they say... 🤖

3

1

88

Gilles Louppe

@glouppe

5 years

I am always speechless at the precision physicists write simulators...

Massimo

@Rainmaker1973

5 years

The first-ever image of a black hole (M87 or Virgo A, left) is here compared with a simulation (middle) and the simulation blurred to the expected resolution of the telescope (right)

14

907

2K

0

15

86

Gilles Louppe

@glouppe

5 years

Tomorrow is already my last Deep Learning lecture of the year! The full deck of (600+) slides can be downloaded at Quite happy with the final result, but relieved at the same time! Now let's hope for the best regarding the outcome of the exam.

1

22

82

Gilles Louppe

@glouppe

7 months

📢 Open PhD position in my group, on simulation-based inference and generative models for particle physics, on a joint project with Fabio Maltoni and Tilman Plehn

0

35

76

Gilles Louppe

@glouppe

2 years

Big news! 🚨 Our workshop got accepted at ICML 2023! Join us to discuss how to combine scientific ⚗️ and ML 🤖 models into hybrid models 🧌. Let's bridge the gap between fields! 🤝 Stay tuned for more details 📻 #ICML2023

0

9

79

Gilles Louppe

@glouppe

3 years

New paper📢"Averting A Crisis In Simulation-Based Inference" -- a huge team effort led by my students @joeri_hermans and @ArnaudDelaunoy

A Trust Crisis In Simulation-Based Inference? Your Posterior...

We present extensive empirical evidence showing that current Bayesian simulation-based inference algorithms can produce computationally unfaithful posterior approximations. Our results show that...

arxiv.org

5

10

79

Gilles Louppe

@glouppe

1 year

The Machine Learning and the Physical Sciences workshop will return for a 6th edition at #NeurIPS2023 ! More info coming soon! 📢🔭⚗️🧲

3

11

78

Gilles Louppe

@glouppe

1 month

Can we run reliable simulation-based inference on a budget? when having as few as O(10-100) simulations? Yes, we can! Check out @ArnaudDelaunoy 's latest paper on Bayesian neural networks for low-budget simulation-based inference 🤓

2

15

76

Gilles Louppe

@glouppe

4 years

What if you want to do posterior inference but don't have a prior to start with? In this new work led by @VandegarM , we investigate how the empirical Bayesian can use neural density estimators to estimate a source distribution over uncorrupted samples from noise-corrupted ones.

1

21

76

Gilles Louppe

@glouppe

7 years

Open PhD position @UniversiteLiege in exoplanet imaging with deep learning. Exciting opportunity to develop ML algorithms for the detection of new planets!

1

40

74

Gilles Louppe

@glouppe

7 months

Very proud to sign my first paper with @ATLASexperiment on "Deep Generative Models for Fast Photon Shower Simulation in ATLAS"! This project actually began in 2017, way before generative AI was cool. It is a relief to see it finally published 🤖

Deep Generative Models for Fast Photon Shower Simulation in ATLAS

Computing and Software for Big Science - The need for large-scale production of highly accurate simulated event samples for the extensive physics programme of the ATLAS experiment at the Large...

link.springer.com

3

9

74

Gilles Louppe

@glouppe

2 years

"The secret to modelling is not being perfect" Warm congratulations to my student @WehenkelAntoine for defending his PhD thesis. Exciting work ahead at @apple with @jh_jacobsen #proudadvisor

8

4

73

Gilles Louppe

@glouppe

2 years

Using neural score estimation for reverse-diffusing a Gaussian into a Bayesian posterior!👇

Gilles Louppe

@glouppe

2 years

New in💡lampe v0.7 by @FrancoisRozet : score-based diffusion models (sub-VP SDEs) for simulation-based inference! Check it out at

0

14

56

0

9

74

Gilles Louppe

@glouppe

2 years

Congratulations to @joeri_hermans , my first student to defend his PhD thesis! before/after 🎊🍻 #proudadvisor

2

73

Gilles Louppe

@glouppe

6 years

Accepted for publication at #AISTATS2019 ! 📜Can't wait to discover Japan!

Gilles Louppe

@glouppe

7 years

It's out! Our latest paper with @KyleCranmer : Adversarial Variational Optimization of Non-Differentiable Simulators

6

91

252

0

14

73

Gilles Louppe

@glouppe

8 years

Want a scatter matrix of the 2D partial dependence of your objective function? @betatim made it for you in `skopt`!

3

24

71

Gilles Louppe

@glouppe

6 years

In our latest paper with Johann Brehmer, @KyleCranmer and @juanpavez , we compare this extraction process to 'mining gold' from implicit models and show how it can dramatically improve data efficiency of likelihood-free inference algorithms.

1

17

69

Gilles Louppe

@glouppe

8 years

The paper behind TensorFlow Fold: Deep Learning with Dynamic Computation Graphs by Norvig et al.

1

27

70

Gilles Louppe

@glouppe

3 years

Simulation-based inference outside of science? Yes! Here is our attempt for robotic multi-fingered grasping 🤖 It took some efforts to bridge the sim-to-reality gap, but adding nuisance parameters was then natural and worked very smoothly.

4

12

67

Gilles Louppe

@glouppe

2 years

Less talking, more action: tomorrow in my deep learning class, I'll be building and training a mini GPT from scratch👨‍💻! It won't rival the largest LLMs 🦙but expect some magical Harry Potter-esque babble✨🪄

4

6

68

Gilles Louppe

@glouppe

6 years

Quite satisfactory to reach a point in my AI class where students should have all the pieces for building an approximately intelligent agent in partially observable stochastic environments, combining algorithms for reasoning over time, handling uncertainty and taking decisions.

2

13

67

Gilles Louppe

@glouppe

6 years

TIL when preparing my second deep learning lecture that the operators' manual for Rosenblatt's Mark 1 Perceptron machine was a classified document. It became unclassified only in 1977. The manual can now be found at

0

20

63

Gilles Louppe

@glouppe

2 years

Mission complete! It took us several hours (almost 4!), but we built and trained a fully-working GPT language model on Harry Potter! The code implemented in class can be found at

Gilles Louppe

@glouppe

2 years

Less talking, more action: tomorrow in my deep learning class, I'll be building and training a mini GPT from scratch👨‍💻! It won't rival the largest LLMs 🦙but expect some magical Harry Potter-esque babble✨🪄

4

6

68

4

12

65

Gilles Louppe

@glouppe

5 years

This is the model from Report 13 of the Imperial College COVID-19 response team. It fits the death data jointly from 11 European countries to estimate the reproduction number and the effect of lockdowns. Such a remarkable piece of @mcmc_stan

4

24

66

Gilles Louppe

@glouppe

6 years

Lecture 2 of my Deep Learning class this morning: from logistic regression to deep rectified networks. Slides at

0

19

65

Gilles Louppe

@glouppe

7 years

Looking for a PhD studentship? Want to develop AI and deep learning for furthering scientific discovery? Let's get in touch! More details at I'll be at #NIPS2017 if you want to chat.

2

35

64

Gilles Louppe

@glouppe

9 years

Our latest paper: Likelihood-free inference with your favorite ML model! @KyleCranmer @juanpavez

5

29

62

Gilles Louppe

@glouppe

7 years

Inspired by , today I tried to distill to my students some intuition behind the effectiveness of deep learning by folding a sheet of paper in front of them. Not sure if they clicked, or if I just lost them...

5

9

61

Gilles Louppe

@glouppe

7 years

By the way, I cannot but recommend @francoisfleuret 's amazingly thorough deep learning course It's been a strong inspiration for those slides.

2

16

61

Gilles Louppe

@glouppe

10 years

Now Dr. in Computer Science! Slides of my PhD defense: Understanding Random Forests - From Theory to Practice http://t.co/viw0zZ9nC7

Understanding Random Forests: From Theory to Practice

Understanding Random Forests: From Theory to Practice - Download as a PDF or view online for free

www.slideshare.net

7

21

57

Gilles Louppe

@glouppe

3 years

The call for papers to our Machine Learning and the Physical Sciences workshop #ML4PS2021 #NeurIPS2021 is now out! The deadline is set a month from now, on September 18.

Kyle Cranmer

@KyleCranmer

3 years

Our Machine Learning for Physical Sciences workshop was accepted for #NeurIPS2021 ! Excellent work by @atilimgunes @BasicScienceSav @glouppe @iamstarnord @BPNachman @carrasqu & Emine Kucukbenli in putting the proposal together. Updates to follow #ML4PS2021

5

63

306

0

23

55

Gilles Louppe

@glouppe

4 years

Now accepted at #aistats2021 ! Congratulations to my incoming PhD student @VandegarM for his first paper! Excited to see what's next :) (with @WehenkelAntoine and @Michael_A_Kagan )

Gilles Louppe

@glouppe

4 years

What if you want to do posterior inference but don't have a prior to start with? In this new work led by @VandegarM , we investigate how the empirical Bayesian can use neural density estimators to estimate a source distribution over uncorrupted samples from noise-corrupted ones.

1

21

76

2

7

59

Gilles Louppe

@glouppe

7 years

That is, I'll start as an Assistant Professor in AI in Fall 2017 :)

10

3

58

Gilles Louppe

@glouppe

2 years

New in💡lampe v0.7 by @FrancoisRozet : score-based diffusion models (sub-VP SDEs) for simulation-based inference! Check it out at

0

14

56

Gilles Louppe

@glouppe

7 years

Dear AI students, study your Bayes' rule. Can't count how often it appears in #NIPS2017 talks

1

9

56

Gilles Louppe

@glouppe

6 years

Excited to have this finally out! In this work, we look to see how a neural network can hijack random number calls in a particle physics simulator for amortized posterior inference. Praises to @atilimgunes and @lukasheinrich_ !

Stat.ML Papers

@StatMLPapers

6 years

Efficient Probabilistic Inference in the Quest for Physics Beyond the Standard Model. (arXiv:1807.07706v1 [cs.LG])

0

3

4

0

13

53

Gilles Louppe

@glouppe

4 years

Exciting news for #AI research in Belgium! Fine print: I will soon be looking for new PhD students to work on AI for science! Prospective applicants are welcome to reach out 🤖🧑‍🎓

La Libre Eco

@LaLibreEco

4 years

Le gouvernement wallon va octroyer 32 millions d'euros au "Trail Institute" pour des projets en intelligence artificielle

0

1

0

2

8

53

Gilles Louppe

@glouppe

4 years

In this first part, I illustrate the change of variables theorem, together with its application for parameter estimation of affine transformations. Purely artificial I concur, but that's nice exercise for getting used to JAX API. Stay tuned for Part 2!

0

9

54

Gilles Louppe

@glouppe

10 years

Accelerating Random Forests in Scikit-Learn. Slides available at http://t.co/1AyhHioh4d @EuroSciPy

Accelerating Random Forests in Scikit-Learn

Accelerating Random Forests in Scikit-Learn - Download as a PDF or view online for free

www.slideshare.net

2

39

55

Gilles Louppe

@glouppe

4 years

2nd paper of the day with friends from @GRAPPAinstitute , incl. @C_Weniger , @NilanjanBanik and @gfbertone ! We haven't solved protein folding, but I am quite excited about this study in which we show the full potential of simulation-based inference for grand scientific problems💫🤖

Gianfranco Bertone

@gfbertone

4 years

New paper today w/ @joeri_hermans , Nil Banik, @C_Weniger and @glouppe : a likelihood-free Bayesian inference pipeline to infer properties of dark matter from observations of stellar streams

2

4

42

2

13

54

Gilles Louppe

@glouppe

8 years

Thrilled to announce our latest paper with @KyleCranmer : Learning to pivot with adversarial nets

3

20

53

Gilles Louppe

@glouppe

6 years

Really impressed by the expressiveness of the latent space of #StyleGAN ! I can map myself into latent space and interpolate to my office neighbor @DamienERNST1

3

9

52

Gilles Louppe

@glouppe

3 years

Quite happy to release our latest short work with @WehenkelAntoine on Diffusion Priors in Variational Autoencoders, accepted at INNF+ 2021 (at ICML)

Diffusion Priors In Variational Autoencoders

Among likelihood-based approaches for deep generative modelling, variational autoencoders (VAEs) offer scalable amortized posterior inference and fast sampling. However, VAEs are also more and...

arxiv.org

3

12

52

Gilles Louppe

@glouppe

7 years

Brilliant conversation between @EtienneKlein and @ylecun : can intelligence be artificial? (in French) Feels refreshing to see a debate of this quality among all the over-hyped AI coverage

Yann LeCun

@ylecun

7 years

Podcast de l'émission "La Pensée Scientifique" animé par Étienne Klein sur France Culture dans laquelle nous...

1

35

57

0

20

53

Gilles Louppe

@glouppe

2 years

All 188 papers and posters accepted to the #ML4PS2022 workshop are now online! Take the time to have a look before arriving at NeurIPS next week!

1

5

51

Gilles Louppe

@glouppe

5 years

The third edition of my "Introduction to AI" class -- a modernized summary of GOFAI -- is now finished! Now is time to relax during the Christmas break 😴 Slides are all available at .

1

20

52

Gilles Louppe

@glouppe

5 years

Hot from your arXiv: a (much) revised version of from my student @joeri_hermans , where we show how to effectively plug approximate likelihood ratios to obtain likelihood-free variants of MCMC algorithms.

2

19

50

Gilles Louppe

@glouppe

8 years

Skopt 0.1 is now released on PyPI! Makes bayesian/model-based optimization as simple as `gp_minimize(f, bounds)`

GitHub - scikit-optimize/scikit-optimize: Sequential model-based optimization with a `scipy.optim...

Sequential model-based optimization with a `scipy.optimize` interface - scikit-optimize/scikit-optimize

github.com

2

34

51

Gilles Louppe

@glouppe

3 years

Meh, rejected from #AISTATS2022 because the "paper focuses too much on applications in astronomy"?! An argument that was not even raised in any of the original reviews... Alright then, we will get a ticket for the next lottery.🎲

Gilles Louppe

@glouppe

3 years

New paper📢"Averting A Crisis In Simulation-Based Inference" -- a huge team effort led by my students @joeri_hermans and @ArnaudDelaunoy

5

10

79

2

1

51

Gilles Louppe

@glouppe

6 years

First paper of the year, by my student @joeri_hermans ! In , we adapt MCMC algorithms to the likelihood-free scenario by making use of a parameterized likelihood ratio model learned by supervised learning.

2

16

50

Gilles Louppe

@glouppe

5 years

👇 Proud of my student who reimplemented almost entirely from scratch a full deep learning pipeline for voice embedding, cloning and synthesis. Let him know what you think!

Corentin Jemine

@CorentinJemine

5 years

The finished product of my master's thesis: a real-time voice cloning toolbox. Clone a voice from only 5 seconds of audio and use it for text-to-speech! #DeepLearning #AI

2

12

41

1

7

51