Institute for Pure & Applied Mathematics (IPAM) Courses

Tensors in Statistics and Data Analysis

Explore tensors in statistics and data analysis, covering probability tensors, biological measurements, and signature tensors for time-series data. Learn about decompositions and algebraic properties in this comprehensive overview.

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

Low Rank Tensor Methods in High Dimensional Data Analysis

Explore advanced tensor methods for analyzing high-dimensional data, focusing on recent developments, challenges, and applications in various scientific fields.

• YouTube
• 1 hour 16 minutes
• On-Demand
• Free Video

How to Allow Deep Learning on Your Data Without Revealing Your Data

Exploring secure deep learning on private data without revealing it, discussing InstaHide and TextHide methods, their applications in Federated Learning, and addressing potential security concerns.

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

Task-Driven Network Discovery via Deep Reinforcement Learning on Embedded Spaces

Explore task-driven network discovery using deep reinforcement learning on embedded spaces. Learn about improving network observability and optimizing data collection for accurate analysis.

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

Task Structure and Generalization in Graph Neural Networks

Explore graph neural networks' generalization properties, focusing on the interplay between task structure and architectural biases for improved learning and performance in algorithmic tasks.

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

Combining Reinforcement Learning and Constraint Programming for Combinatorial Optimization

Explore a hybrid approach combining reinforcement learning and constraint programming for solving complex combinatorial optimization problems, with applications in various fields.

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

Deep Learning for Combinatorial Optimization - Count Your Flops & Make Your Flops Count

Explores deep learning for combinatorial optimization, focusing on reducing computation through learned models while balancing solution quality. Discusses practical examples, challenges, and future research directions.

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

How Much Data Is Sufficient to Learn High-Performing Algorithms?

Explore data-driven algorithm design's impact on performance, focusing on generalization guarantees for combinatorial algorithms with piecewise-structured parameter functions.

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

Reasoning on Natural Inputs

Explore neural algorithmic reasoning for natural inputs, bridging classical algorithms with deep learning to solve real-world problems more effectively in reinforcement learning environments.

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

A Framework for Differentiable Discovery of Graph Algorithms

Explore graph algorithm discovery using deep learning and tree decomposition. Learn effective techniques for NP-complete problems with interpretable results and expanded search space.

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

Can ML Help in Solving Cargo Capacity Management Booking Control Problems

Explore ML applications in cargo capacity management, focusing on booking control problems and predicting solution costs for discrete optimization in revenue management.

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

Neural Network Verification as Piecewise Linear Optimization

Neural network verification as piecewise linear optimization: exploring robust methods to prove model reliability against attacks, using LP and MIP formulations for efficient problem-solving in various network types.

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

The Transformer Network for the Traveling Salesman Problem

Explore how Transformer networks can tackle the Traveling Salesman Problem, improving upon existing heuristics with promising results for combinatorial optimization challenges.

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

Fair and Interpretable Decision Rules for Binary Classification

Explore fair and interpretable decision rules for binary classification using Boolean rule sets in DNF, with a focus on maximizing accuracy while maintaining group fairness constraints.

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

Schrödinger Bridges - Classical and Quantum

Explore Schrödinger bridges in classical and quantum contexts, their applications to Markov chains and quantum channels, and their solutions for probability distributions and state evolutions.

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