Christoph Molnar @ChristophMolnar Twitter profile

Pinned Tweet

Christoph Molnar

7 months

Happy to publish our book project “Supervised Machine Learning for Science” today 🥳 Read it for free here: The book is about the philosophical and pragmatic justification for using supervised machine learning in science.

10

80

381

Last Seen Profiles

@BabyDosh14

@subathirran

@layahimalaya

@Orchidya_

@sr_tqk

@BinorRaja

@stw_pdg

@yurilovesHTS

@hyeok__kim

@KAPI_torihiki

@BarstoolOakland

@levicoralynn

@Jakal_SS

@ruamamiya

@grebmeg

@OmeTvDoods

@jesikaonly

@hifdzikhoir

@fetichesunga

@rachelheck2020

@ArchitypeUK

@timeextension64

@willytoballs

@BinorRaja

@e7banat

@tanaka_medical

@xiaoangel_1005

@OdinsLuck

@RadioImpound

@TamDentist76

@kkbugtime

@Kluchh

@itsiceithink

@SimGamezzz

@bokeplokalmalam

@Queen__SoFi

Christoph Molnar

@ChristophMolnar

2 years

BREAKING: IBM makes game-changing move, invests $42 in ChatGPT Pro to revolutionize IBM Watson capabilities

143

564

9K

Christoph Molnar

@ChristophMolnar

6 months

I have the solution for detecting AI-generated text.

232

268

5K

Christoph Molnar

@ChristophMolnar

6 years

2 years, 250 pages, 1,219 commits, and 78,480 words: I am very proud to say that today I published the 1st edition of "Interpretable Machine Learning". 🎉🎉🎉 Web: Leanpub:

71

1K

4K

Christoph Molnar

@ChristophMolnar

4 years

When your machine learning model is confronted with data it has not been trained on.

63

723

4K

Christoph Molnar

@ChristophMolnar

2 years

You can't "train" a model. The model always exists. It existed before you were born and it exists after your death. You can only find the model. "Training" is just your way of looking for the model's location in the infinite hypothesis space and binding its essence to silicon

199

319

4K

Christoph Molnar

@ChristophMolnar

2 years

I write my books with vim. Why tough? While there are many good reasons to use Vim for book writing, one stands out: I don't know how to exit Vim.

81

238

4K

Christoph Molnar

@ChristophMolnar

4 years

Machine Learning concepts as animal GIFs A thread 🧵

53

1K

4K

Christoph Molnar

@ChristophMolnar

2 years

Watching the k-means cluster slowly converge

35

393

3K

Christoph Molnar

@ChristophMolnar

11 months

Ready to nerd out on random forests? Someone wrote an entire Ph.D. thesis on random forests ❤️ 200 pages of gems. Highlights: Why ensembles work, interpretability of forests, and making random forests work on huge datasets.

15

487

3K

Christoph Molnar

@ChristophMolnar

3 years

A lot of machine learning research has detached itself from solving real problems, and created their own "benchmark-islands". How does this happen? And why are researchers not escaping this pattern? A thread 🧵

54

719

3K

Christoph Molnar

@ChristophMolnar

1 year

22

199

2K

Christoph Molnar

@ChristophMolnar

8 months

Evaluating a model on training data is like asking your mom if you look good.

41

289

2K

Christoph Molnar

@ChristophMolnar

11 months

The mean is the best prediction model • Needs no features • Easy to compute • No overfitting • Interpretable • Optimizes L2 • Analytical solution

118

139

2K

Christoph Molnar

@ChristophMolnar

1 year

Not many people know this, but one milestone in becoming an ML researcher is getting blocked by Lex Fridman on Twitter.

85

101

2K

Christoph Molnar

@ChristophMolnar

3 years

12

342

2K

Christoph Molnar

@ChristophMolnar

1 year

Neural networks with only linear layers would result in linear models. Because a linear combination of linear functions is again linear. Nothing would be gained by adding more layers.

Daniel Bourke

@mrdbourke

1 year

ML folks, does anyone have a good resource/explanation for *why* the use of non-linear functions (e.g. ReLU) in neural networks and why they work so well? My simplified version is: Combine enough straight (linear) and non-straight (non-linear) lines and you can draw a

103

58

593

33

183

2K

Christoph Molnar

@ChristophMolnar

10 months

"Machine Learning is just statistics." I thought as I entered my first Kaggle competition. Turned out to be a harsh reality check: ML and statistical modeling require different mindsets. This haunted me for many years, so I wrote it all down in my book Modeling Mindsets.

12

227

2K

Christoph Molnar

@ChristophMolnar

3 years

Where are you on your machine learning journey?

17

190

2K

Christoph Molnar

@ChristophMolnar

8 months

I just found a great introduction to embedding. The book is comprehensive yet short. Historical encoding tools, neural nets, and production - all covered. Fantastic job by @vboykis . Thanks for making it free to read! Looking forward to diving in.

5

276

1K

Christoph Molnar

@ChristophMolnar

6 months

Will this now happen with every new LLM update?

19

193

1K

Christoph Molnar

@ChristophMolnar

2 years

Some dude at a BBQ once asked me what I do. I said research in ML / AI Dude went off into an angry rant about surveillance, killer robots, and self-driving cars. No chance to tell him my work is most useful for data stored in Excel for some boring process in an insurance corp.

29

54

1K

Christoph Molnar

@ChristophMolnar

1 month

"Machine Learning is just statistics." I thought as I entered my first Kaggle machine learning competition. Turned out to be a harsh reality check: ML and statistical modeling require different mindsets. This haunted me for many years, so I wrote the book Modeling Mindsets.

10

161

1K

Christoph Molnar

@ChristophMolnar

4 years

What do you call a machine learning model that perfectly predicts the training data, but does not work for unseen data? A database

40

131

1K

Christoph Molnar

@ChristophMolnar

1 year

How it started: f(X) = X How it's going: • is f AGI? • f might be conscious • f will conquer the world • You can use premium f for $20 a month • f is only 14 weeks old and here is what you can do. • Here are 10 products of f(X)=X you haven't heard of

30

173

1K

Christoph Molnar

@ChristophMolnar

2 years

I "grew up" as a statistician. When I later learned about machine learning, I found it a mind-blowing new perspective on data modeling. The best data modelers don't ideologically follow one mindset but have many at their disposal. But which modeling mindsets are there? 🧵

15

200

1K

Christoph Molnar

@ChristophMolnar

2 years

Progress in generative AI Past: Cherry-pick good results Now: Cherry-pick bad results

15

75

1K

Christoph Molnar

@ChristophMolnar

2 years

Novice data scientist: Data is data. Expert data scientist: Each data column has a difficult past. A past full of life-altering events (distribution shift), loss (missing data), misunderstandings (wrong encodings), and regrets (no documentation of how data was collected).

11

187

1K

Christoph Molnar

@ChristophMolnar

2 months

My book Interpretable Machine Learning has been career-defining. Even though the book is available on the web for free, many have supported me by buying the ebook or paperback, which ultimately helped me become a full-time writer. I'm grateful for all your support 🙏

13

163

1K

Christoph Molnar

@ChristophMolnar

7 years

The first version of my online book on Interpretable Machine Learning is out! I am very excited to release it. It's a guide for making machine learning models explainable. #interpretableML #iml #ExplainableAI #xai #MachineLearning #DataScience

16

463

1K

Christoph Molnar

@ChristophMolnar

2 years

Machine learning sucks at uncertainty quantification. But there is a solution that almost sounds too good to be true: conformal prediction • works for any black box model • requires few lines of code • is fast • comes with statistical guarantees A thread 🧵

20

140

976

Christoph Molnar

@ChristophMolnar

3 years

LASSO is the Marie Kondo of linear regression models

6

169

916

Christoph Molnar

@ChristophMolnar

1 year

This is used as an example of a Gaussian distribution. But it's not a pure Gaussian. We must increase the nerd level: It's a mixture distribution of a discretized and truncated Gaussian with 0 and 135 (?) cut-offs and a Dirac delta function at 100.

A meme page to check every time MatLab crashes

@memecrashes

1 year

gauss 🤝🏽 gymbros

127

5K

63K

16

98

896

Christoph Molnar

@ChristophMolnar

2 years

Studying statistics was one of the best decisions I made. After finishing school, I had no idea what industry I wanted to work in. I liked math. So I chose statistics. It's like having a janitor's key ring that gives me access to any industry. I never looked back.

22

93

889

Christoph Molnar

@ChristophMolnar

3 years

No amount of deep learning can fix bad data. Modeling is fun, good data is hard work. Improving data can mean - going through hand-written records - building a labeling interface yourself - find out why data is missing - investigating the "trail" of the data - weeks of curation

13

139

864

Christoph Molnar

@ChristophMolnar

3 years

compute resources

7

92

874

Christoph Molnar

@ChristophMolnar

4 years

We have a new paper on arxiv 🎉🎉 Interpretable Machine Learning - A Brief History, State-of-the-Art and Challenges. Best to read in a comfortable chair with a cup of coffee/tea. It's an extended abstract to a keynote I gave at the ECML XKDD workshop.

Interpretable Machine Learning -- A Brief History,...

We present a brief history of the field of interpretable machine learning (IML), give an overview of state-of-the-art interpretation methods, and discuss challenges. Research in IML has boomed in...

arxiv.org

18

217

842

Christoph Molnar

@ChristophMolnar

11 months

I'm calling for a more minimalistic approach to machine learning: Regression? Predict the mean Robust regression? Median Classification? Always predict majority class Time series? Same as yesterday: Y(t) = Y(t-1) Text generation? Lorem ipsum

27

71

838

Christoph Molnar

@ChristophMolnar

2 years

Bayesians: "Join us! Updating prior believes is exactly how humans learn." Causal inference: "Join us! Humans think in causal relationships." Machine learning: "Join us! Models are black boxes and so are humans." 1/2

6

119

822

Christoph Molnar

@ChristophMolnar

3 years

Reinventing the wheel

7

117

814

Christoph Molnar

@ChristophMolnar

2 years

Most ML interpretation methods have a common enemy: Correlated features. They ruin interpretation both on a technical and a philosophical level. Why correlation is problematic, how to patch it, and why we have no cure. A thread 🧵

17

171

809

Christoph Molnar

@ChristophMolnar

1 year

Machine learning interpretability from first principles: • A model is just a mathematical function • The function can be broken down into simpler parts • Interpretation methods address the behavior of these parts Let's dive in.

3

126

796

Christoph Molnar

@ChristophMolnar

1 year

It took me a long time to understand Bayesian statistics. So many angles from which to approach it: the Bayes' Theorem, probability as a degree of belief, Bayesian updating, priors and posteriors, ... But my favorite angle is the following first principle :

8

116

779

Christoph Molnar

@ChristophMolnar

2 years

Regression models usually just output a point prediction. That's a problem. Because the prediction could be spot on or it could be a wild guess. To distinguish these two scenarios, we need uncertainty quantification. A solution: Conformal Prediction 1/n

17

118

769

Christoph Molnar

@ChristophMolnar

3 years

Statisticians and Data Scientists

7

60

751

Christoph Molnar

@ChristophMolnar

1 year

Bayesian modeling from first principle and memes. Let's go.

15

124

750

Christoph Molnar

@ChristophMolnar

2 years

SHAP, LIME, PFI, ... you can interpret ML models with many different methods. It's all fun and games until two methods disagree. What if LIME says X1 has a positive contribution, SHAP says negative? A thread about the disagreement problem, and how to approach it:

19

139

745

Christoph Molnar

@ChristophMolnar

4 years

@MMsina @marielli In Germany we call this "Waschmaschinenfremdbenutzungsabsicherung" and you can buy it at the Baumarkt. No, just kidding. What's wrong with the neighbour?

7

8

728

Christoph Molnar

@ChristophMolnar

2 years

Simply apply SHAP and other methods to interpret your machine learning model, paste those charts into a report and you're done? Unfortunately, if you do, you're likely to make a mistake. Avoid these pitfalls when interpreting your machine learning model.👇

12

167

744

Christoph Molnar

@ChristophMolnar

11 months

Been doing ML for some years now. Here's my ranking: Supervised ⭐️⭐️ ⭐️ ⭐️ ⭐️ Self-supervised ⭐️ ⭐️ ⭐️ ⭐️ Reinforcement Learning ⭐️ Unsupervised 🚮

52

45

721

Christoph Molnar

@ChristophMolnar

2 years

Unpopular (?) opinion: Scientific papers are designed to be defensive which comes at the expense of honesty and readability. I blame the peer review system.

33

42

724

Christoph Molnar

@ChristophMolnar

3 years

Finally, the second edition of Interpretable Machine Learning is here! 🥳🥳🥳 So far only as e-book. Paperback should be available shortly (and in color!). Leanpub: Amazon:

Interpretable Machine Learning: A Guide For Making Black Box Models Explainable

www.amazon.com

11

119

687

Christoph Molnar

@ChristophMolnar

2 years

Data science cannot be fully automated. No amount of parameter tuning, benchmarking, automation, model comparison, automated feature engineering, etc., can automatically figure out what data column location_123_old contains and whether it should be a feature or not.

26

80

645

Christoph Molnar

@ChristophMolnar

2 years

Supervised learning "only" gives you a prediction function. But with the right tools, you'll get a lot more: • Uncertainty quantification • Causality • Interpretability • Analysis of variance • ... And the best news: tools in this thread work for any black box model 👇

8

102

618

Christoph Molnar

@ChristophMolnar

2 years

It's overwhelming to keep up with research on interpretable machine learning. I say that as the author of the Interpretable Machine Learning book. 😅 I use these 3 questions to quickly understand new interpretation methods:

11

99

618

Christoph Molnar

@ChristophMolnar

2 years

Super excited to release my new book Modeling Mindsets tomorrow 🥳 This is my first book since I decided to become a full-time writer. And it's the book I wish I had read a few years ago to save myself a lot of time. 1/n

10

80

615

Christoph Molnar

@ChristophMolnar

6 months

I'm hoping developers take the AI dev thing seriously. Self-driving cars were introduced in the mid-2010s. Look at all the fools who got their driver's license nonetheless and now have a worthless document. Or think of all the jobless radiologists trying to make ends meet.

31

68

615

Christoph Molnar

@ChristophMolnar

2 years

I found it unexpectedly difficult to get into causal inference. (still a beginner, I guess) Here are a few insights that helped me in understanding causal inference. 🧵

16

64

574

Christoph Molnar

@ChristophMolnar

4 years

Logistic Regression sold as AI

2

48

586

Christoph Molnar

@ChristophMolnar

3 years

If you were to learn only 1 method for explaining machine learning models, it should be Shapley values (SHAP) - Model-agnostic: Use with any model - Theoretic foundation: Game theory - Good software ecosystem - Local and global explanations More here:

9.5 Shapley Values | Interpretable Machine Learning

Machine learning algorithms usually operate as black boxes and it is unclear how they derived a certain decision. This book is a guide for practitioners to make machine learning decisions interpret...

christophm.github.io

16

83

581

Christoph Molnar

@ChristophMolnar

2 years

One of the best arguments for supervised learning was made by a statistician. Statistical Modeling: The Two Cultures Every modeler should read it. The paper is written by Leo Breiman, the inventor of Random Forests.

11

106

580

Christoph Molnar

@ChristophMolnar

3 years

Early on, I had made "Interpretable Machine Learning" (web + e-book) available for 0$. I never regretted the decision, and I happily share my knowledge. And yet so many of you opted to pay for the e-book, encouraging me on my path of free knowledge. I am grateful 🙏

7

30

561

Christoph Molnar

@ChristophMolnar

3 years

How COVID ML papers are created

9

101

558

Christoph Molnar

@ChristophMolnar

2 years

The modeling mindset of statisticians in one tweet 1) Measure random variables, e.g. water temperature 2) Assume distribution, e.g. Normal distribution 3) Goal: Find optimal distribution parameters, e.g. mean 4) Solution: Maximize the likelihood Parameters = Insight about world

10

80

548

Christoph Molnar

@ChristophMolnar

3 years

Statistics, Machine Learning, Causal Inference, ... People coming from these different modeling cultures often have misunderstandings, and fight over whether logistic regression is "AI" or statistics. Why the big differences? 1/n 🧵

8

133

549

Christoph Molnar

@ChristophMolnar

2 years

This tweet is 20% food for thought 80% shitposting Thank you for your attention

17

6

542

Christoph Molnar

@ChristophMolnar

3 years

Missing data in a random forest.

The Spooky Lawyer | QENNY

@AKBrews

3 years

What is this?

4K

17K

160K

10

58

522

Christoph Molnar

@ChristophMolnar

5 years

What are some limitations of interpretable machine learning methods? This summer, our students worked on this question. We compiled the results in a free online book, which we release today. 🎉🎉🎉 Find out more:

12

168

510

Christoph Molnar

@ChristophMolnar

7 months

To become a statistician, you must study the divine numbers: 30 represents sufficiency 0.049 is a sign of good fortune 1.96 protects you from uncertainty 0.051 says that your career is in danger

8

48

502

Christoph Molnar

@ChristophMolnar

6 months

I don't get why people still use SQL???? • Rejects most prompts. Requires specific prompting. • 100% overfitting to training data • No generalization to new data • Non-stochastic parrots

26

40

502

Christoph Molnar

@ChristophMolnar

2 years

Supervised machine learning models are deployed everywhere. It's an open secret that all models have a huge problem: Performative prediction - when predictions change future outcomes. How to spot and handle this problem: A thread 🧵

19

85

492

Christoph Molnar

@ChristophMolnar

3 years

When machine learning researchers reinvent methods from statistics.

8

73

485

Christoph Molnar

@ChristophMolnar

2 months

I see what you did there. Love the title.

18

33

495

Christoph Molnar

@ChristophMolnar

1 year

Statistical modeling from first principle. But with memes and GIFs. Let's start.

4

118

481

Christoph Molnar

@ChristophMolnar

3 years

We assume linearity

6

75

471

Christoph Molnar

@ChristophMolnar

7 months

3 days left. Looking forward to the release of Supervised Machine Learning for Science.

9

50

471

Christoph Molnar

@ChristophMolnar

2 years

Most machine learning applications fail. Google Flu, Amazon hiring, ML in healthcare, ... Why? A wide range of reasons. But most are due to the same flaw: not thinking through the problem as a statistician would. Adopt a statistician's mindset. Become a better machine learner

17

67

459

Christoph Molnar

@ChristophMolnar

2 years

tabular -> import xgboost text -> from transformers import pipeline image -> import torch, torchvision chat -> import langchain thanks for coming to my TED talk

10

35

461

Christoph Molnar

@ChristophMolnar

2 years

Modeling Mindsets is published 🥳 From Bayesian inference to unsupervised learning: Modeling Mindsets provides an intuitive introduction to different modeling approaches and allows you to choose the right one for your problem. Get your copy at:

Modeling Mindsets

leanpub.com

21

86

459

Christoph Molnar

@ChristophMolnar

2 years

Is linear regression machine learning or stats? is like asking Is an apple a fruit or is it something to eat?

35

30

452

Christoph Molnar

@ChristophMolnar

4 years

Some examples how interpretable machine learning (IML) is used for scientific discovery, when the underlying model is a black box model. A few examples. Thread 1/n

8

110

441

Christoph Molnar

@ChristophMolnar

2 years

I once met a professor who was OBSESSED with h-index and citations. - Advised me to stop my book, turn it into a paper to get cited - Output not published at icml/ neurips? Worthless - Gave a talk - it was only about flashing status symbols Absolutely corrupted by THE GAME.

22

23

437

Christoph Molnar

@ChristophMolnar

3 years

The more I dive into machine learning targeting COVID, the more I believe that the research impact is not zero, but negative. Negative, bc. many prediction models are low quality, unusable. Waste of time + resources. Adding noise to an already crazy publishing environment.

17

63

429

Christoph Molnar

@ChristophMolnar

3 years

Welcome to academia

4

27

431

Christoph Molnar

@ChristophMolnar

2 years

Deep learning crowd getting novel models.

5

53

422

Christoph Molnar

@ChristophMolnar

1 year

My new book, Interpreting Machine Learning Models With SHAP is now also available as a paperback (in color)! 🎉 SHAP is the Swiss army knife of ML interpretability and this book is a comprehensive guide to the theory and application of SHAP.

5

41

420

Christoph Molnar

@ChristophMolnar

1 year

Looking for a career in AI? I have you covered.

8

41

403

Christoph Molnar

@ChristophMolnar

10 months

Follow me for more tips on how to sound smart

8

19

406

Christoph Molnar

@ChristophMolnar

7 months

7 years ago, I wrote the first chapters of Interpretable Machine Learning. I didn't know back then, but this was the start of my writing career. In 4 days, I'll publish a new book project. Online. Free access. In many ways, it weaves together many threads of my career.

18

27

396

Christoph Molnar

@ChristophMolnar

7 months

Bias-variance tradeoff, generalization error, no free lunch theorem -> These concepts come from statistical learning theory which views supervised machine learning through a statistics lens. It's heavy on math and theory. Bookmark the best entry point:

Statistical Learning Theory: Models, Concepts, and Results

Statistical learning theory provides the theoretical basis for many of today's machine learning algorithms. In this article we attempt to give a gentle, non-technical overview over the key ideas...

arxiv.org

1

57

394

Christoph Molnar

@ChristophMolnar

3 years

Interpretable Machine Learning has >2000 citations 🥳 This reminds me of the professor who laughed at me when I told him that people were citing the book (8 citations at the time) and told me, "You should turn the book into review paper so you can get citations." 🤷‍♂️

8

21

396

Christoph Molnar

@ChristophMolnar

2 years

I have started to create cheat sheets for model interpretation. So far: • Logistic regression: • SHAP plots for tabular data: They are free (pay what you want) Do you have any topic wishes for the next cheat sheets?

Logistic Regression - Interpretation Cheat Sheet

I've studied statistics for 5 years, worked in statistical consulting and used statistical models for research.And I still have to look up the interpretation of logistic regression again and again....

christophmolnar.gumroad.com

16

60

390

Christoph Molnar

@ChristophMolnar

4 years

A lot of interpretation methods for machine learning are connected to other fields Game Theory -> Shapley Values Philosophy -> Counterfactuals Sensitivity Analysis -> model-agnostic methods Statistical Modeling -> linear model, GAMs Rule-Based ML -> Decision trees What else?

16

56

388

Christoph Molnar

@ChristophMolnar

6 months

@gunesevitan AI-generated text was detected.

1

2

379

Christoph Molnar

@ChristophMolnar

6 months

@wolftreeMtg which is the truth and proof that this solution is premium

0

1

377

Christoph Molnar

@ChristophMolnar

10 months

Two types of Bayesians 1) Beer pub Bayesian: People who want to be seen as intelligent by using words like "Bayesian", "prior", "posterior", "updating" to refer to the fact that people have opinions and sometimes change their minds. 2) Actual Bayesian who analyzes data

22

30

365

Christoph Molnar

@ChristophMolnar

2 years

Are researchers putting too much burden on this smol boy?

2

38

365

Christoph Molnar

@ChristophMolnar

4 years

"You should turn your book into a paper so that it gets cited." "You have to publish at ICML/ECML to have any impact." It can be difficult to decide when to follow conventional advice and when not. I am happy I did the unconventional with Interpretable Machine Learning.

12

37

364

Christoph Molnar

@ChristophMolnar

2 years

9

77

354

Christoph Molnar

@ChristophMolnar

7 years

Most common arguments against interpretable ML: - Humans can't explain their actions either - Performance > Interpretability - Slows down ML adoption - Linear model also not interpretable - Might create illusion of understanding the model Thread:

10

155

353