Simons Institute Courses

Analyzing Optimization and Generalization in Deep Learning via Dynamics of Gradient Descent

Explore deep learning optimization and generalization through gradient descent dynamics, focusing on implicit preconditioning and its impact on matrix completion problems.

• YouTube
• 44 minutes
• Self-Paced
• Free Video

Recent Progress in Algorithmic Robust Statistics via the Sum-of-Squares Method

Explore recent advancements in algorithmic robust statistics using the Sum-of-Squares method, focusing on learning and testing in high-dimensional spaces.

• YouTube
• 51 minutes
• Self-Paced
• Free Video

Offline Reinforcement Learning and Model-Based Optimization

Explore offline reinforcement learning and model-based optimization techniques, focusing on data-driven approaches, Q-function lower bounds, and model inversion networks for automated decision-making.

• YouTube
• 34 minutes
• Self-Paced
• Free Video

Multiagent Reinforcement Learning: Rollout and Policy Iteration

Explore finite-state multiagent reinforcement learning through policy iteration and rollout, focusing on trading off control and state complexity in infinite horizon problems.

• YouTube
• 37 minutes
• Self-Paced
• Free Video

Beyond Worst-Case: Instance-Dependent Optimality in Reinforcement Learning

Explore instance-dependent optimality in reinforcement learning, focusing on policy evaluation and TD learning. Gain insights into achieving optimal algorithms and useful bounds.

• YouTube
• 44 minutes
• Self-Paced
• Free Video

Reinforcement Learning

Explore reinforcement learning's foundations, applications, and advanced concepts, including Q-learning, exploration-exploitation trade-offs, and instance-optimality in policy evaluation.

• YouTube
• 31 minutes
• Self-Paced
• Free Video

Algorithms with Prediction

Explore how machine learning predictions can enhance traditional algorithms, improving efficiency in search, caching, and data structures like Bloom filters.

• YouTube
• 30 minutes
• Self-Paced
• Free Video

Economics and Learning

Explore the intersection of economics and machine learning, focusing on game theory, recommendation systems, and decentralized models in data science.

• YouTube
• 31 minutes
• Self-Paced
• Free Video

What Are the Statistical Limits of Offline Reinforcement Learning With Function Approximation?

Explore statistical limitations in offline reinforcement learning with function approximation, covering realizability, coverage, policy evaluation, and practical considerations.

• YouTube
• 55 minutes
• Self-Paced
• Free Video

Model-Based Reinforcement Learning with Value-Targeted Regression

Explore model-based reinforcement learning with value-targeted regression, covering episodic RL, UCRL, deterministic systems, and the MatrixRL algorithm.

• YouTube
• 36 minutes
• Self-Paced
• Free Video

The Ethical Algorithm

Explore ethical challenges in algorithmic design, focusing on data privacy and fairness. Learn about differential privacy, anonymization techniques, and defining fairness in AI systems.

• YouTube
• 1 hour 29 minutes
• Self-Paced
• Free Video

A Slightly Improved Approximation Algorithm for Metric TSP

Explore an improved approximation algorithm for the Metric Traveling Salesman Problem, focusing on 2-uniform spanning trees and probabilistic techniques in algorithm design.

• YouTube
• 46 minutes
• Self-Paced
• Free Video

Safe Learning in Robotics

Explore safe learning in robotics, covering reachable sets, collision avoidance, fast planning, and human-robot interaction. Gain insights into cutting-edge techniques for autonomous systems.

• YouTube
• 55 minutes
• Self-Paced
• Free Video

Deep Robust Reinforcement Learning and Regularization

Explore robust reinforcement learning, addressing uncertainties in deep RL through regularization techniques. Gain insights into robust MDPs, policy evaluation, and uncertainty-aware Bellman equations.

• YouTube
• 31 minutes
• Self-Paced
• Free Video

Mixed Autonomy Traffic: A Reinforcement Learning Perspective

Explore reinforcement learning for mixed autonomy traffic, focusing on counterfactual reasoning, urban simulation, and transfer learning to address societal challenges in transportation.

• YouTube
• 32 minutes
• Self-Paced
• Free Video