Simons Institute Courses

From Classical Statistics to Modern Machine Learning

Explore the evolution from classical statistics to modern machine learning, examining key concepts like generalization, interpolation, and the "double descent" phenomenon in supervised learning.

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

Practical Model-Based Algorithms for Reinforcement Learning and Imitation Learning

Explore efficient model-based algorithms for reinforcement and imitation learning, addressing challenges in learning dynamics and uncertainty, with practical examples and evaluations.

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

Benign Overfitting in Linear Prediction

Explore the phenomenon of benign overfitting in linear prediction, its implications for deep learning, and its impact on adversarial examples in machine learning.

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

Disentangling Influence: Using Disentangled Representations to Audit Model Predictions

Explore disentangled representations to audit model predictions, examining direct and indirect influence, independent factors, and experimental results in fairness research.

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

The Measure and Mismeasure of Fairness

Explore quantitative approaches to fairness in machine decisions, examining assumptions, risk distributions, and popular mathematical definitions through real-world case studies.

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

What is Your Data Worth? Equitable Data Valuation in Machine Learning

Explore equitable data valuation in machine learning, focusing on Data Shapley Value and its applications in healthcare, face recognition, and NLP.

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

Generative Models

Explore generative models in deep learning, covering theoretical perspectives, hacker models, information flow, and provable algorithms for learning classifiers and phylogenetic reconstruction.

• YouTube
• 1 hour 8 minutes
• Self-Paced
• Free Video

Implicit Regularization I

Explore implicit regularization in deep learning, covering boosting, complexity control, optimization landscapes, and stochastic gradient descent for effective model training.

• YouTube
• 1 hour 17 minutes
• Self-Paced
• Free Video

Nearest Neighbors I

Explore nearest neighbor algorithms in machine learning, covering regression, classification, consistency, and convergence rates in metric spaces. Gain insights into statistical learning frameworks and smoothness conditions.

• YouTube
• 1 hour 8 minutes
• Self-Paced
• Free Video

Adversarial Examples

Explore the intriguing world of adversarial examples in deep learning, their implications, and theoretical frameworks with expert Sébastien Bubeck from Microsoft Research.

• YouTube
• 1 hour 24 minutes
• Self-Paced
• Free Video

Recent Developments in Over-parametrized Neural Networks, Part I

Explore recent developments in over-parametrized neural networks, focusing on optimization challenges, theoretical problems, and strategies for achieving optimal results in deep learning.

• YouTube
• 1 hour 14 minutes
• Self-Paced
• Free Video

Generalization II

Explore advanced concepts in deep learning, including random averages, losses, and network architectures, with experts from UC Berkeley and MIT.

• YouTube
• 1 hour 23 minutes
• Self-Paced
• Free Video

Generalization I

Explore deep learning generalization with experts Peter Bartlett and Sasha Rakhlin, covering perceptron algorithms and key concepts in machine learning theory.

• YouTube
• 1 hour 17 minutes
• Self-Paced
• Free Video

Individual Statistical Fairness

Explore statistical fairness in machine learning, focusing on individual-level impacts and false negative rates beyond differential privacy.

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

Classical Zero Knowledge Arguments for Quantum Computing

Explore zero-knowledge arguments in quantum computing, covering delegation protocols, quantum NP, and classical commitment to quantum states.

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