Toward Understanding In-Context Learning
Dive into the mechanisms of in-context learning in large language models, exploring theoretical explanations and simplified data distributions with Stanford's Tengyu Ma.
Learning Probability Distributions - What Can, What Can't Be Done - Shai Ben-David
Explore probability distribution learning, its possibilities and limitations. Shai Ben-David discusses density estimation, sample compression schemes, and challenges in statistical learning theory.
Latent Stochastic Differential Equations for Irregularly-Sampled Time Series - David Duvenaud
Explore advanced techniques for analyzing irregularly-sampled time series data using latent stochastic differential equations, with applications in predictive modeling and continuous-time machine learning.
Interpolation in Learning - Steps Towards Understanding When Overparameterization Is Harmless, When It Helps, and When It Causes Harm
Explore overparameterization in machine learning, its benefits, potential harm, and the double descent phenomenon. Gain insights into interpolation regimes and matrix intuition.
Your Brain on Energy-Based Models - Applying and Scaling EBMs to Problems
Explore energy-based models in machine learning, covering applications, scaling techniques, and their impact on classification, calibration, and robustness in AI systems.
Understanding Deep Neural Networks - From Generalization to Interpretability
Explore deep neural networks, focusing on generalization and interpretability. Delve into graph convolutional networks, spectral filtering, and transferability. Examine fundamental questions and relevance mapping in machine learning.
Latent State Recovery in Reinforcement Learning - John Langford
Explore latent state recovery in reinforcement learning, covering core problems, alternative approaches, and state abstraction. Gain insights from John Langford's expertise in theoretical machine learning.
On the Critic Function of Implicit Generative Models - Arthur Gretton
Explore implicit generative models' critic function, divergence measures, and energy-based models with Arthur Gretton. Gain insights into topological properties, neural net divergences, and multimodality in machine learning.
Priors for Semantic Variables - Yoshua Bengio
Explore semantic variables, learning theory, and cognitive processes with Yoshua Bengio. Delve into attention mechanisms, causality, and modular recurrent networks for advanced machine learning insights.
Instance-Hiding Schemes for Private Distributed Learning
Explore private distributed learning techniques, including instance-hiding schemes, cryptographic methods, and data augmentation, with insights on privacy laws and practical applications.
Optimization Landscape and Two-Layer Neural Networks - Rong Ge
Explore optimization landscapes and two-layer neural networks, focusing on non-convexity, saddle points, and symmetric distributions in theoretical machine learning.
Faster Saddle-Point Optimization for Solving Large-Scale Markov Decision Processes
Explore advanced techniques for optimizing large-scale Markov decision processes using saddle-point methods. Gain insights into theoretical reinforcement learning and linear programming formulations.