collaborators

5 papers

cs.LG2026

Algorithmic Separation between Constant-Depth and Logarithmic-Depth Neural Networks

Yunwei Ren, Zihao Wang, Jason D. Lee

Despite the empirical advantages of deep networks over shallow ones, theoretical depth separations largely concern approximation power, while algorithmic results are mostly limited…

cs.LG2026

Phase Transitions for Feature Learning in Neural Networks

Andrea Montanari, Zihao Wang

According to a popular viewpoint, neural networks learn from data by first identifying low-dimensional representations, and subsequently fitting the best model in this space. Recen…

stat.ML2026

Non-negative matrix factorization algorithms generally improve topic model fits

Peter Carbonetto, Abhishek Sarkar, Zihao Wang +1

In an effort to develop topic modeling methods that can be quickly applied to large data sets, we revisit the problem of maximum-likelihood estimation in topic models. It is known,…

stat.ML2026

Neural Networks Learn Generic Multi-Index Models Near Information-Theoretic Limit

Bohan Zhang, Zihao Wang, Hengyu Fu +1

In deep learning, a central issue is to understand how neural networks efficiently learn high-dimensional features. To this end, we explore the gradient descent learning of a gener…

math.OC2025

A Linear Complexity Algorithm for Optimal Transport Problem with Log-type Cost

Ziyuan Lyu, Zihao Wang, Hao Wu +1

In [Q. Liao et al., Commun. Math. Sci., 20(2022)], a linear-time Sinkhorn algorithm is developed based on dynamic programming, which significantly reduces the computational complex…