Simons Institute Courses

Pseudo-Labeling for Covariate Shift Adaptation in Machine Learning

Explore advanced covariate shift adaptation techniques using pseudo-labeling methods for regression tasks, focusing on kernel ridge regression and bias-variance optimization for target distributions.

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

Causally Motivated Robustness to Shortcut Learning in Machine Learning

Delve into techniques for building robust machine learning models that maintain performance under distribution shifts, with a focus on preventing shortcut learning through causal regularization methods.

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

Open-Source and Science in the Era of Foundation Models

Explore the critical role of open-source models in AI development, focusing on API access, open weights, and community-driven innovation for advancing foundation model research.

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

Language-Guided Domain Adaptation

Explore cutting-edge techniques in domain adaptation and language-guided methods with UC Berkeley expert Trevor Darrrell, focusing on advanced machine learning applications and methodologies.

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

Toward Understanding the Extrapolation of Nonlinear Models to Unseen Domains

Explore advanced concepts in domain adaptation and model extrapolation, focusing on nonlinear models' behavior in unseen domains through theoretical and practical analysis.

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

Adaptive Data Collection via Autoregressive Generation in News Recommendation Systems

Discover how autoregressive models can enhance adaptive data collection and decision-making through Thompson sampling, with applications in news recommendation systems and cold-start problems.

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

Scalably Understanding AI with AI - Using AI Systems for Model Behavior Analysis

Explore advanced techniques for analyzing AI systems, from behavior elicitation to neuron description, focusing on using AI tools to understand and improve AI model behaviors and representations.

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

Domain Adaptation and Related Areas in Machine Learning

Dive into domain adaptation concepts and related machine learning areas with Carnegie Mellon expert Zachary Lipton, exploring theoretical frameworks and practical applications.

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

Domain Adaptation - 20 Years of Theory Chasing Practice

Explore the evolving relationship between theoretical frameworks and practical applications in domain adaptation learning, examining key insights, challenges, and the widening theory-practice gap.

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

Neuroscience and AI - A Symbiosis

Explore the intricate relationship between neuroscience and artificial intelligence, examining how LLMs intersect with cognitive science, linguistics, and brain function.

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

Building Scalable Systems for Automatically Understanding Large Language Models

Explore cutting-edge approaches to analyzing and understanding Large Language Models through scalable automated systems, focusing on cognitive science and linguistics perspectives.

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

Lattice-Based Post-Quantum iO from Circular Security with Random Opening Assumption

Explore advanced cryptographic techniques for building secure post-quantum indistinguishability obfuscation using lattice-based methods and novel security assumptions.

• YouTube
• 1 hour 4 minutes
• On-Demand
• Free Video

Lattice Assumptions with Hints - Succinct LWE and its Applications

Explore succinct Learning With Errors (LWE) assumptions and their cryptographic applications in lattice-based obfuscation techniques.

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

Computational Wiretap Coding from Indistinguishability Obfuscation

Explore computational wiretap coding using indistinguishability obfuscation to enable secure communication over noisy channels while hiding messages from adversaries.

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

Beyond P versus NP - Using Complexity Theory in Obfuscation and Vice-Versa

Explore advanced cryptographic constructions using indistinguishability obfuscation, combining complexity theory beyond P≠NP to achieve optimal hardness guarantees in encryption and one-way functions.

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