25 citations · 38 across the 9 of their papers we have counts for
9 papers
Self-Improvement in Language Models: The Sharpening Mechanism
Audrey Huang, Adam Block, Dylan J. Foster +5
Recent work in language modeling has raised the possibility of self-improvement, where a language models evaluates and refines its own generations to achieve higher performance wit…
Butterfly Effects of SGD Noise: Error Amplification in Behavior Cloning and Autoregression
Adam Block, Dylan J. Foster, Akshay Krishnamurthy +2
This work studies training instabilities of behavior cloning with deep neural networks. We observe that minibatch SGD updates to the policy network during training result in sharp…
Statistical Learning under Heterogeneous Distribution Shift
Max Simchowitz, Anurag Ajay, Pulkit Agrawal +1
This paper studies the prediction of a target from a pair of random variables , where the ground-truth predictor is additive $\mathbb{E}[\math…
Oracle-Efficient Smoothed Online Learning for Piecewise Continuous Decision Making
Adam Block, Alexander Rakhlin, Max Simchowitz
Smoothed online learning has emerged as a popular framework to mitigate the substantial loss in statistical and computational complexity that arises when one moves from classical t…
Smoothed Online Learning for Prediction in Piecewise Affine Systems
Adam Block, Max Simchowitz, Russ Tedrake
The problem of piecewise affine (PWA) regression and planning is of foundational importance to the study of online learning, control, and robotics, where it provides a theoreticall…
Efficient and Near-Optimal Smoothed Online Learning for Generalized Linear Functions
Adam Block, Max Simchowitz
Due to the drastic gap in complexity between sequential and batch statistical learning, recent work has studied a smoothed sequential learning setting, where Nature is constrained…
Bayesian decision-making under misspecified priors with applications to meta-learning
Max Simchowitz, Christopher Tosh, Akshay Krishnamurthy +4
Thompson sampling and other Bayesian sequential decision-making algorithms are among the most popular approaches to tackle explore/exploit trade-offs in (contextual) bandits. The c…
Learning the Linear Quadratic Regulator from Nonlinear Observations
Zakaria Mhammedi, Dylan J. Foster, Max Simchowitz +5
We introduce a new problem setting for continuous control called the LQR with Rich Observations, or RichLQR. In our setting, the environment is summarized by a low-dimensional cont…
Reward-Free Exploration for Reinforcement Learning
Chi Jin, Akshay Krishnamurthy, Max Simchowitz +1
Exploration is widely regarded as one of the most challenging aspects of reinforcement learning (RL), with many naive approaches succumbing to exponential sample complexity. To iso…