activity
20222026
most citedA Flexible Approach for Normal Approximation of Geometric and Topological Statistics

1 citations · 1 across the 7 of their papers we have counts for

collaborators

9 papers

stat.ME2026

Population-Level Generative Modeling for Ranking Data

Zhaoyang Shi

Ranking data arise in scientific and machine learning applications, including recommendation systems, information retrieval, voting, marketing, and AI preference ranking from human…

math.ST2026

Optimal Demixing of Nonparametric Densities

Jianqing Fan, Zheng Tracy Ke, Zhaoyang Shi

Motivated by applications in statistics and machine learning, we consider a problem of unmixing convex combinations of nonparametric densities. Suppose we observe groups of sam…

cs.LG2025

Dense Associative Memory with Epanechnikov Energy

Benjamin Hoover, Zhaoyang Shi, Krishnakumar Balasubramanian +2

We propose a novel energy function for Dense Associative Memory (DenseAM) networks, the log-sum-ReLU (LSR), inspired by optimal kernel density estimation. Unlike the common log-sum…

cs.LG2025

Community-based Multi-Agent Reinforcement Learning with Transfer and Active Exploration

Zhaoyang Shi

We propose a new framework for multi-agent reinforcement learning (MARL), where the agents cooperate in a time-evolving network with latent community structures and mixed membershi…

math.ST2024

Gaussian and Bootstrap Approximation for Matching-based Average Treatment Effect Estimators

Zhaoyang Shi, Chinmoy Bhattacharjee, Krishnakumar Balasubramanian +1

We establish Gaussian approximation bounds for covariate and rank-matching-based Average Treatment Effect (ATE) estimators. By analyzing these estimators through the lens of stabil…

math.ST2024

Multivariate Gaussian Approximation for Random Forest via Region-based Stabilization

Zhaoyang Shi, Chinmoy Bhattacharjee, Krishnakumar Balasubramanian +1

We derive Gaussian approximation bounds for -Potential Nearest Neighbor (-PNN) based random forest predictions based on a set of training points given by a Poisson process un…