activity
20202026
most citedOn Riemannian Optimization over Positive Definite Matrices with the Bures-Wasserstein Geometry

8 citations · 22 across the 18 of their papers we have counts for

collaborators
Showing cs.LGShow all

21 papers · 1 filter

cs.LG2026

Nearly Tight Rademacher Bounds for Sparsely Activated Neural Networks

Xiaoyu Li, Zhizhou Sha, Jiaojiao Jiang +2

An input may activate few hidden units even when different inputs collectively use an entire network. We study the statistical complexity of this input-dependent sparsity in the on…

cs.LG2026

Feature Superposition in Neural Networks: From Theory to Practice

Dai Shi, Xiaoyu Li, Andi Han +1

Superposition refers to neural networks representing more features than they have dimensions. It offers a possible explanation for polysemantic neurons and motivates methods for re…

cs.LG2026

Optimistic Rates for Multiclass PAC Learning

Xiaoyu Li, Andi Han, Jiaojiao Jiang +1

Worst-case multiclass bounds do not become smaller when the best classifier is already nearly correct: what is missing is an optimistic rate, a guarantee whose fluctuation scales w…

cs.LG2026

Flood and Harvest: The Provable Necessity of Trivia for Generating Valuable Mathematics via the Lens of Language Generation in the Limit

Xiaoyu Li, Andi Han, Dai Shi +3

AI systems coupled to proof assistants now generate formal mathematics at scale, and the gap between what a checker can verify and what a mathematician would value has become the b…

cs.LG2026

Learning Manifold and Itô Dynamics with Branched Neural Rough Differential Equations

Luke Thompson, Dai Shi, Lequan Lin +2

Neural rough differential equations (NRDEs) stay accurate under irregular sampling while taking far fewer integration steps than standard neural differential equations, summarising…

cs.LG2026

SGNN: Efficient Global Mixing and Local Message Passing for Long-Range Graph Learning

Dai Shi, Luke Thompson, Linhan Luo +4

Message-passing neural networks (MPNNs) often suffer from an information bottleneck when capturing long-range dependencies, leading to the oversquashing (OSQ) phenomenon. Alongside…