Podcast cover
Institute for Pure & Applied Mathematics (IPAM) · Science

Institute for Pure & Applied Mathematics (IPAM)

The Institute for Pure and Applied Mathematics (IPAM) is a National Science Foundation Math Institute at the University of California, Los Angeles (UCLA) that fosters the interaction of mathematics with a broad range of science and technology, builds new interdisciplinary research communities, promotes mathematical innovation, and engages and transforms the world through mathematics. IPAM fulfills its mission through workshops and programs that connect mathematics and other disciplines or multiple areas of mathematics. These activities bring in thousands of visitors annually from academia, government, and industry. The NSF has encouraged IPAM to make the scientific presentations of our speakers available to a wider audience. While this YouTube channel contains many of our most popular videos, our full video archive is available at www.ipam.ucla.edu/videos.

Episodes

Episode cover

Shaowei Lin - Singular Learning, Relative Information and the Dual Numbers - IPAM at UCLA

16 Oct 2024
49m
Episode cover

Dan Roy - Size of Teachers as Measure of Data Complexity: PAC-Bayes Excess Risk Bounds & Scaling Law

16 Oct 2024
56m
Episode cover

Patrick Shafto - Common Ground in Cooperative Communication - IPAM at UCLA

16 Oct 2024
50m
Episode cover

Sam Smith - How to train an LLM - IPAM at UCLA

15 Oct 2024
53m
Episode cover

Vidya Muthukumar - Comparison and transfer between tasks in overparameterized learning

15 Oct 2024
49m
Episode cover

Gintare Karolina Dziugaite - The dynamics of memorization and generalization in deep learning

15 Oct 2024
51m
Episode cover

Cengiz Pehlevan - 2 stories in mechanistic interpretation of natural & artificial neural computation

15 Oct 2024
54m
Episode cover

Elvis Dohmatob - The Mathematics of Scaling Laws and Model Collapse in AI - IPAM at UCLA

14 Oct 2024
1h 3m
Episode cover

Nikos Tsilivis - The Price of Implicit Bias in Robust ML - IPAM at UCLA

14 Oct 2024
46m
Episode cover

Wu Lin - A framework for designing (non-diagonal) adaptive training methods - IPAM at UCLA

14 Oct 2024
49m
Episode cover

Boris Hanin - Neural Network Scaling Limits - IPAM at UCLA

14 Oct 2024
1h 0m
Episode cover

Stanislav Minsker - New performance guarantees for Tukey’s median - IPAM at UCLA

27 Sep 2024
49m
Episode cover

James Pascoe - Beyond physical maze solvers via modern portfolio theory - IPAM at UCLA

27 Sep 2024
46m
Episode cover

Natalia Velez - Games as a window into large-scale social phenomena - IPAM at UCLA

27 Sep 2024
1h 0m
Episode cover

James Evans - Diversity, Disconnection, Discord, and Other Properties of Collective Intelligence

27 Sep 2024
55m
Episode cover

Gregory Beylkin - On algorithms in high dimensions - IPAM at UCLA

27 Sep 2024
50m
Episode cover

Cynthia Flores - From Materials to Minds: Nonlocal Approaches to Damage and Degeneration

26 Sep 2024
55m
Episode cover

Tobias Gerstenberg - Counterfactual simulation in causal cognition - IPAM at UCLA

26 Sep 2024
1h 1m
Episode cover

Max Kleiman-Weiner - Reverse-Engineering Human Cooperation - IPAM at UCLA

26 Sep 2024
56m
Episode cover

Joel Leibo - Studying the behavior of generative AI-based agents in multi-agent systems

26 Sep 2024
1h 1m
Page 31

Follow this podcast in Podwise

Sign in to get AI summaries, transcripts and mind maps for any episode, including new ones.

Open in Podwise