Picture for Krishnakumar Balasubramanian

Krishnakumar Balasubramanian

Department of Statistics, University of California, Davis

Provable In-context Learning for Mixture of Linear Regressions using Transformers

Add code
Oct 18, 2024
Viaarxiv icon

Transformers Handle Endogeneity in In-Context Linear Regression

Add code
Oct 02, 2024
Viaarxiv icon

Improved Finite-Particle Convergence Rates for Stein Variational Gradient Descent

Add code
Sep 13, 2024
Viaarxiv icon

Stochastic Optimization Algorithms for Instrumental Variable Regression with Streaming Data

Add code
May 29, 2024
Viaarxiv icon

A Separation in Heavy-Tailed Sampling: Gaussian vs. Stable Oracles for Proximal Samplers

Add code
May 27, 2024
Viaarxiv icon

Minimax Optimal Goodness-of-Fit Testing with Kernel Stein Discrepancy

Add code
Apr 12, 2024
Viaarxiv icon

Meta-Learning with Generalized Ridge Regression: High-dimensional Asymptotics, Optimality and Hyper-covariance Estimation

Add code
Mar 27, 2024
Viaarxiv icon

Multivariate Gaussian Approximation for Random Forest via Region-based Stabilization

Add code
Mar 26, 2024
Viaarxiv icon

Nonsmooth Nonparametric Regression via Fractional Laplacian Eigenmaps

Add code
Feb 22, 2024
Viaarxiv icon

Adaptive and non-adaptive minimax rates for weighted Laplacian-eigenmap based nonparametric regression

Add code
Oct 31, 2023
Viaarxiv icon