Simons Institute Courses

Min-Max Optimization - Part I

Explore min-max optimization, equilibrium computation, and adversarial gradient descent in zero-sum games, connecting classical techniques to deep learning applications.

• YouTube
• 1 hour 3 minutes
• On-Demand
• Free Video

Introduction to Causal Graphical Models - Graphs, D-Separation, Do-Calculus

Explore causal graphical models, d-separation, and do-calculus. Learn about graphs, Bayesian networks, and instrumental variables for understanding causality in complex systems.

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

Equivariant Machine Learning Structured Like Classical Physics

Explore equivariant machine learning and its connection to classical physics, focusing on graph neural networks, spectral methods, and symmetry in optimization problems.

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

Equivariant RL

Explore equivariant reinforcement learning, its advantages, and applications in graph neural networks with Max Welling from the University of Amsterdam.

• YouTube
• 1 hour 9 minutes
• On-Demand
• Free Video

Making Predictions in a Quantum World - Quantum Colloquium

Explore quantum predictions: efficient learning methods, impossible problems, and how quantum technology enhances our predictive capabilities in physics and chemistry.

• YouTube
• 1 hour 2 minutes
• On-Demand
• Free Video

Yes, Generative Models Are The New Sparsity

Explore how generative models revolutionize data compression and signal processing, offering new perspectives on sparsity and optimization in machine learning.

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

Finding Large Cliques in Random and Semi-Random Graphs

Explore algorithms for finding large cliques in graphs, including constructive arguments, polynomial-time proofs, and paradigms for tackling this NP-hard problem.

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

Locally Testable Codes with Constant Rate, Distance, and Locality

Explore breakthroughs in locally testable codes, focusing on constant rate, distance, and locality. Irit Dinur discusses high-dimensional expanders, Tanner codes, and local testability proofs.

• YouTube
• 1 hour 7 minutes
• On-Demand
• Free Video

Computational Barriers in Statistical Estimation and Learning

Explore statistical estimation challenges, information theory, and computational barriers in high-dimensional settings with Stanford's Andrea Montanari in this Richard M. Karp Distinguished Lecture.

• YouTube
• 1 hour 3 minutes
• On-Demand
• Free Video

Optimal Gradient-Based Algorithms for Non-Concave Bandit Optimization

Explore optimal gradient-based algorithms for non-concave bandit optimization, covering stochastic problems, low-rank linear rewards, and high-order polynomials with applications to reinforcement learning.

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

Optimal Transport and PDE - Gradient Flows in the Wasserstein Metric

Explore gradient flows in Wasserstein metric, continuity equations, and aggregation dynamics. Learn about two-layer neural networks and chi-squared divergence in optimization and sampling.

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

Crash Course on Optimal Transport

Explore optimal transport theory, its applications, and key concepts like cost formulation, optimal coupling, and transport maps in this comprehensive lecture.

• YouTube
• 1 hour 2 minutes
• On-Demand
• Free Video

Sampling Crash Course

Explore geometric methods in optimization and sampling, covering direct methods, Markov chain Monte Carlo, and probabilistic approaches for efficient algorithm design and analysis.

• YouTube
• 1 hour 3 minutes
• On-Demand
• Free Video

Optimization Crash Course

Explore geometric methods in optimization and sampling, covering key topics like convexity, optimality, and gradient descent with expert insights from MIT's Ashia Wilson.

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

Approximate Message Passing Algorithms

Explore Approximate Message Passing algorithms, their applications in statistical inference, and theoretical foundations including state evolution, convergence, and joint distribution analysis.

• YouTube
• 1 hour 7 minutes
• On-Demand
• Free Video