Institute for Advanced Study Courses

What Do Our Models Learn? - Aleksander Mądry

Exploring machine learning model behavior, biases in datasets, and challenges in dataset creation and replication for more robust and reliable AI systems.

• YouTube
• 1 hour 28 minutes
• On-Demand
• Free Video

Mirrors of Curves and Their Fukaya Categories - Denis Auroux

Explore symplectic geometry with Denis Auroux as he delves into mirrors of curves and their Fukaya categories, covering topics from monomial examples to Lagrangian admissibility.

• YouTube
• 1 hour 19 minutes
• On-Demand
• Free Video

Neural SDEs - Deep Generative Models in the Diffusion Limit - Maxim Raginsky

Explore deep generative models through stochastic control, diffusion limits, and neural nets. Learn about efficient sampling, expressiveness quantification, and unbiased simulation techniques.

• YouTube
• 1 hour 20 minutes
• On-Demand
• Free Video

The Non-Stochastic Control Problem - Elad Hazan

Explore advanced control theory for linear dynamical systems, covering adversarial noise, general loss functions, unknown systems, and partial observation in robotics, finance, and engineering.

• YouTube
• 58 minutes
• On-Demand
• Free Video

Reflections on Cylindrical Contact Homology - Jo Nelson

Explore cylindrical contact homology, its evolution, and recent developments in symplectic geometry with Jo Nelson's in-depth seminar on periodic orbits and obstruction bundles.

• YouTube
• 1 hour 6 minutes
• On-Demand
• Free Video

A Geometric View on Iwasawa Theory - Mladen Dimitrov

Explore a geometric perspective on Iwasawa theory, covering higher dimensions, periodic representations, and key concepts in number theory with Mladen Dimitrov from Université de Lille.

• YouTube
• 1 hour 11 minutes
• On-Demand
• Free Video

Generative Modeling by Estimating Gradients of the Data Distribution - Stefano Ermon

Explore generative modeling through gradient estimation of data distributions, covering deep energy-based models, score matching, and innovative sampling techniques for improved AI generation.

• YouTube
• 1 hour 21 minutes
• On-Demand
• Free Video

Using Discrepancy Theory to Improve the Design of Randomized Controlled Trials - Daniel Spielman

Explore discrepancy theory's application in randomized controlled trials, enhancing experimental design and statistical analysis for more accurate and efficient research outcomes.

• YouTube
• 1 hour 10 minutes
• On-Demand
• Free Video

Learning Probability Distributions - What Can, What Can't Be Done - Shai Ben-David

Explore probability distribution learning, its possibilities and limitations. Shai Ben-David discusses density estimation, sample compression schemes, and challenges in statistical learning theory.

• YouTube
• 57 minutes
• On-Demand
• Free Video

Latent Stochastic Differential Equations for Irregularly-Sampled Time Series - David Duvenaud

Explore advanced techniques for analyzing irregularly-sampled time series data using latent stochastic differential equations, with applications in predictive modeling and continuous-time machine learning.

• YouTube
• 1 hour 5 minutes
• On-Demand
• Free Video

Ellipses of Small Eccentricity Are Determined by Their Dirichlet - Steven Morris Zelditch

Explore the spectral analysis of ellipses with small eccentricity, focusing on Dirichlet and Neumann spectra, caustic billiard tables, and periodic orbits in nearly circular domains.

• YouTube
• 1 hour 15 minutes
• On-Demand
• Free Video

Graph and Hypergraph Sparsification - Luca Trevisan

Explore graph and hypergraph sparsification techniques with Luca Trevisan, covering spectral definitions, irregular graphs, and unweighted graphs. Gain insights into advanced discrete mathematics concepts.

• YouTube
• 1 hour 34 minutes
• On-Demand
• Free Video

Assumption-Free Prediction Intervals for Black-Box Regression Algorithms - Aaditya Ramdas

Explore assumption-free prediction intervals for regression algorithms, covering split conformal prediction, CQR, full conformal prediction, and jackknife intervals with practical examples.

• YouTube
• 1 hour 22 minutes
• On-Demand
• Free Video

Geodesically Convex Optimization - Can We Prove P!=NP Using Gradient Descent - Avi Wigderson

Explore geodesically convex optimization and its potential to prove P≠NP using gradient descent in this advanced seminar by renowned mathematician Avi Wigderson.

• YouTube
• 1 hour 58 minutes
• On-Demand
• Free Video

Steps Towards More Human-Like Learning in Machines - Josh Tenenbaum

Explore how machines can achieve more human-like learning through probabilistic programming, intuitive psychology, and simulation engines. Discover insights on core knowledge and one-shot learning in AI.

• YouTube
• 1 hour 14 minutes
• On-Demand
• Free Video