Csaba Szepesvari

Sep 16, 2024

Csaba Szepesvari, a leading figure in machine learning and reinforcement learning expert at Google DeepMind, dives deep into the fascinating world of AI. He discusses the balance between theory and practice in neural networks and explores the debate around model-based versus model-free approaches. The chat touches on 'relevance realization,' the core question of what we should focus on in our learning processes. Additionally, Csaba shares personal insights about the challenges of reconciling scientific pursuits with metaphysical beliefs, providing a thought-provoking conclusion.

Ask episode

AI Snips

Chapters

Transcript

Episode notes

INSIGHT

Theory Defines What’s Possible

Theory sharpens what is possible and how to improve algorithms by formalizing precise objectives.
Csaba argues math helps judge whether learning methods are broadly useful beyond single tasks.

INSIGHT

Probabilistic Guarantees Explained

Randomness enters ML via randomized algorithms and random data collection assumptions.
Probabilistic guarantees describe repeatable data-generation processes, not absolute truth.

ANECDOTE

Theorists Waited For Practical Proof

Csaba recounts how theoreticians initially ignored neural nets until practical success forced attention.
He notes theorists gravitated to problems where available tools made progress feasible.

Get the Snipd Podcast app to discover more snips from this episode

Get the app

Csaba Szepesvári is a prominent figure in machine learning and artificial intelligence, particularly known for his contributions to reinforcement learning. He is a professor in the Department of Computing Science at the University of Alberta and a Senior Staff Research Scientist at Google DeepMind.

Our goal in life: keep eating Yann Lecun's cherry (inside joke, ask GPT).

This was a wide-reaching conversation with my good friend Csaba. The first 50 minutes is about AI, we give you insight into what AI researchers and practitioners are dealing behind the scenes, a bit of history and practice of AI.

At around 49 minutes we discuss Yann Lecun's view on model-based planning and reinforcement learning, which is one of the most interesting and far-reaching discussion within AI (should we model the world or just learn to reach goals?).

This naturally leads into relevance realization: what to learn predict and what to ignore, which is the most important question of AGI.

The last 20 minutes it turns more personal, we talk about our life as scientists, the metaphysical no man's land (nonreductionist naturalist metaphysics), and my wrestling with Christianity.

If you like this, check out my conversations with Yogi Jaeger https://www.youtube.com/watch?v=5UJ4y2L2qpk, Anna Riedl https://www.youtube.com/watch?v=w2ZiSWZNQsg, and Giuseppe Paolo https://www.youtube.com/watch?v=R7tEd65e2i8.

00:00:00 Intro.

00:02:39 Google Deep Mind and leading the Foundations team. Theory tells what is possible, and how to do it? What does theory add to practice in machine learning?

00:08:58 Probabilistic guarantees. Sorting vs machine learning. Random algorithms and random data.

00:15:57 Theory and practice. Support vector machines, boosting, and neural nets. History of AI. Practice-driven ML.

00:24:34 Neural nets: history and practice. The fiddliness and the robustification. Overfitting. Overparameterization vs classical statistics. Label noise and regularization.

00:35:06 Reinforcement learning. Learning to behave. Learning to collect data.

00:39:10 Why did we get into AI: to understand intelligence and ourselves.

00:41:48 Reinforcement learning: model of an intelligent agent. Theory: wrt a fully informed agent, how much do you lose by having to learn?

00:49:17 To model or not to model? Model-based reinforcement learning.

00:58:18 Latent representation of importance, relevance realization. Steelmanning and criticizing Yann Lecun's cherry metaphor. Relevance vs simplicity. The shiny object syndrome.

01:12:40 The Jaeger - Riedl - Djedovic - Vervaeke - Walsh paper on naturalizing relevance realization.

01:24:12 Fear and technology. Regulation, freedoms, open source.

01:33:00 Framing precedes observation.

01:35:60 Subjectivity of science. Can we be part of the world we study?

01:43:55 The metaphysical no man's land: nonreductionist naturalism.

01:48:00 Why am I not yet a Christian? Omnipotence and lack of embodiment, rituals that focus on our responsibility of what is below.

I, scientist blog: https://balazskegl.substack.com

Twitter: https://twitter.com/balazskegl

Artwork: DALL-E

Music: Bea Palya https://www.youtube.com/channel/UCBDp3qcFZdU1yoWIRpMSaZw

Hosted on Acast. See acast.com/privacy for more information.