Esha Singh — accepted AI-conference papers

2026

Divide and Learn: Multi-Objective Combinatorial Optimization at Scale

Esha Singh, Dongxia Wu, Chien-Yi Yang, Tajana Rosing, Rose Yu, Yian Ma

ICML 2026poster

Multi-objective combinatorial optimization seeks Pareto-optimal solutions over exponentially large discrete spaces, yet existing methods sacrifice generality, scalability, or theoretical guarantees. We reformulate it as an online learning problem over a decomposed decision space, solving position-wi…

Cited by 0 Source ↗Scholar ↗

2024

Stable Minima Cannot Overfit in Univariate ReLU Networks: Generalization by Large Step Sizes

Dan Qiao, Kaiqi Zhang, Esha Singh, Daniel Soudry, Yu-Xiang Wang

NeurIPS 2024spotlight

We study the generalization of two-layer ReLU neural networks in a univariate nonparametric regression problem with noisy labels. This is a problem where kernels (\emph{e.g.} NTK) are provably sub-optimal and benign overfitting does not happen, thus disqualifying existing theory for interpolating (0…

Cited by 4 Source ↗PDF ↗Scholar ↗