
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


Jianfeng Zhang: "Set Values for Mean Field Games with Multiple Equilibriums"

Paola Mannucci: "Deterministics Mean Field Games with control on the acceleration"

Alpár Mészáros: "Global well-posedness of master equations for deterministic displacement convex..."

Nicolás García Trillos: "From clustering with graph cuts to isoperimetric inequalities..."

Pratik Chaudhari: "Learning with few labeled data"

Quanquan Gu: "Learning Over-parameterized Neural Networks: From Neural Tangent Kernel to Mean-fi..."

Rebecca Willett: "Learning to Solve Inverse Problems in Imaging"

Christopher Finlay: "Training neural ODEs for density estimation"

Wuchen Li: "Accelerated Information Gradient Flow"

Tom Goldstein: "An empirical look at generalization in neural nets"

Hossein Mobahi: "Differential Operators for Generating Structured Adversarial Examples"

Anthony Yezzi: "Accelerated Optimization in the PDE Framework"

Yunan Yang: "The joint power of deterministic and Bayesian approaches for seismic inverse problems"

Irène Waldspurger: "Rank optimality of the Burer-Monteiro factorization"

Mikhail Belkin: "Optimization for over-parameterized systems of non-linear equations"

Maxim Raginsky: "A mean-field theory of lazy training in two-layer neural nets"

Eldad Haber: "Active learning and experimental design - who should we test?"

Peng Chen: "Projected Stein variational methods for high-dimensional Bayesian inversion"

Maxime Laborde: "A Lyapunov analysis for accelerated gradient methods: From deterministic to sto..."
Follow this podcast in Podwise
Sign in to get AI summaries, transcripts and mind maps for any episode, including new ones.
