Publications

Concept algebra for (score-based) text-controlled generative models

This paper concerns the structure of learned representations in txt-guided generative models, focusing on score-based models. A key …
URL

Relaxing the i.i.d. assumption: Adaptively minimax optimal regret via root-entropic regularization

We consider prediction with expert advice when data are generated from distributions varying arbitrarily within an unknown constraint …
URL

Concept Algebra for Text-Controlled Vision Models

This paper concerns the control of text-guided generative models, where a user provides a natural language prompt and the model …
PDF

Tuning Stochastic Gradient Algorithms for Statistical Inference via Large-Sample Asymptotics

The tuning of stochastic gradient algorithms (SGAs) for optimization and sampling is often based on heuristics and trial-and-error …
URL

Minimax Optimal Quantile and Semi-Adversarial Regret via Root-Logarithmic Regularizers

URL

Approximations of Geometrically Ergodic Reversible Markov Chains

A common tool in the practice of Markov Chain Monte Carlo is to use approximating transition kernels to speed up computation when the …
URL

Sharpened Generalization Bounds based on Conditional Mutual Information and an Application to Noisy, Iterative Algorithms

The information-theoretic framework of Russo and J. Zou (2016) and Xu and Raginsky (2017) provides bounds on the generalization error …
URL

In Defense of Uniform Convergence: Generalization via derandomization with an application to interpolating predictors

We propose to study the generalization error of a learned predictor h^ in terms of that of a surrogate (potentially randomized) …
URL

Optimal Scaling and Shaping of Random Walk Metropolis via Diffusion Limits of Block-IID Targets

This work extends Roberts et al. (1997) by considering limits of Random Walk Metropolis (RWM) applied to block IID target …
URL

Information-Theoretic Generalization Bounds for SGLD via Data-Dependent Estimates

In this work, we improve upon the stepwise analysis of noisy iterative learning algorithms initiated by Pensia, Jog, and Loh (2018) and …
URL