The Thesis Review

[24] Martin Arjovsky - Out of Distribution Generalization in Machine Learning

Apr 30, 2021

01:02:48

Creator website

AI Summary

Highlights

AI Chapters

Episode notes

Podcast summary created with Snipd AI

Quick takeaways

Exploration in reinforcement learning is crucial for human-like problem-solving strategies.

Future machine learning approaches may shift towards simpler, more efficient models.

Addressing out-of-distribution generalization challenges in large models requires innovative methods like Invariant Risk Minimization.

Deep dives

Importance of Exploration in Reinforcement Learning

Exploration in reinforcement learning is seen as fundamental due to humans' efficient problem-solving strategies based on uncertainty reduction. The interest in exploration is not only related to out-of-distribution generalization but also encompasses broader areas like uncertainty estimation, anomaly detection, and curriculum learning.

Did Machine Learning Lead to a PhD in Machine Learning?

03:07

Neural Neural Networks - Is There a Path to Generalization?

03:40

Is There a Key Idea Behind Invariant Risk Minimization?

02:03

Introduction

2min

The Role of Rigorous Mathematical Rationality in Deep Learning Research

3min

Writing a Paper

2min

How to Write a Paper on the Theorem

2min

How Did You Come Up With the Need for Formalization of Mathematics?

2min

Do You Have a Favorite Area of Mathematics?

3min

Machine Learning

2min

Did Machine Learning Lead to a PhD in Machine Learning?

3min

PhD - What Was It Like at the Beginning of the PhD?

4min

10.

Wasterstein Gan - Was It Really a Novel Approach?

2min

11.

I Was Like Okay What's the Next Problem to Think About?

2min

12.

Is There a Causality in Graphs?

5min

13.

Optimization and the Out of Distribution Generalization

2min

14.

Is There a Connection Between Machine Learning and Learning Algorithms?

3min

15.

Neural Neural Networks - Is There a Path to Generalization?

4min

16.

Is There a Key Idea Behind Invariant Risk Minimization?

2min

17.

Is There a Best Theoretical Property That This Has?

2min

18.

The Thome Transversality Theorem in Differential Topology

2min

19.

Is There a Gap Between IRM and IRM?

3min

20.

Is There a Difference Between Overparameterized and Not?

2min

21.

The Decision Process for Doing a Postdoc

4min

22.

Is the Exploration Problem Related to Uncertainty?

2min

23.

Do You Think Your PHD Process Has Changed Over Time?

3min

24.

One Piece of Advice for a New Researcher

3min

Martin Arjovsky is a postdoctoral researcher at INRIA. His research focuses on generative modeling, generalization, and exploration in RL. Martin's PhD thesis is titled "Out of Distribution Generalization in Machine Learning", which he completed in 2019 at New York University. We discuss his work on the influential Wasserstein GAN early in his PhD, then discuss his thesis work on out-of-distribution generalization which focused on causal invariance and invariant risk minimization. Episode notes: https://cs.nyu.edu/~welleck/episode24.html Follow the Thesis Review (@thesisreview) and Sean Welleck (@wellecks) on Twitter, and find out more info about the show at https://cs.nyu.edu/~welleck/podcast.html Support The Thesis Review at www.patreon.com/thesisreview or www.buymeacoffee.com/thesisreview

Get the Snipd
podcast app

Unlock the knowledge in podcasts with the podcast player of the future.

AI-powered
podcast player

Listen to all your favourite podcasts with AI-powered features

Discover
highlights

Listen to the best highlights from the podcasts you love and dive into the full episode

Save any
moment

Hear something you like? Tap your headphones to save it with AI-generated key takeaways

Share
& Export

Send highlights to Twitter, WhatsApp or export them to Notion, Readwise & more

AI-powered
podcast player

Listen to all your favourite podcasts with AI-powered features

Discover
highlights

Listen to the best highlights from the podcasts you love and dive into the full episode

The Thesis Review

[24] Martin Arjovsky - Out of Distribution Generalization in Machine Learning

Podcast summary created with Snipd AI

Quick takeaways

Deep dives

Importance of Exploration in Reinforcement Learning

Innovation in Machine Learning Paradigm

Challenges of Out-of-Distribution Generalization in Practical Settings

Evolution of Research Goals During PhD Journey

Advice for New Researchers

Did Machine Learning Lead to a PhD in Machine Learning?

Neural Neural Networks - Is There a Path to Generalization?

Is There a Key Idea Behind Invariant Risk Minimization?

Get the Snipd
podcast app

AI-powered
podcast player

Discover
highlights

Save any
moment

Share
& Export

AI-powered
podcast player

Discover
highlights

The Thesis Review

[24] Martin Arjovsky - Out of Distribution Generalization in Machine Learning

Podcast summary created with Snipd AI

Quick takeaways

Deep dives

Importance of Exploration in Reinforcement Learning

Innovation in Machine Learning Paradigm

Challenges of Out-of-Distribution Generalization in Practical Settings

Evolution of Research Goals During PhD Journey

Advice for New Researchers

Did Machine Learning Lead to a PhD in Machine Learning?

Neural Neural Networks - Is There a Path to Generalization?

Is There a Key Idea Behind Invariant Risk Minimization?

Get the Snipdpodcast app

AI-poweredpodcast player

Discoverhighlights

Save anymoment

Share& Export

AI-poweredpodcast player

Discoverhighlights

Get the Snipd
podcast app

AI-powered
podcast player

Discover
highlights

Save any
moment

Share
& Export

AI-powered
podcast player

Discover
highlights