298 citations · 1.2k across the 24 of their papers we have counts for
9 papers · 1 filter
NowcastDiT: Diffusion Transformers are Effective Precipitation Nowcasters
Haoran Xu, Xingzhuo Guo, Yuchen Zhang +3
Precipitation nowcasting demands accurate short-term forecasts under strong spatiotemporal variability. Diffusion models are well suited to modeling complex precipitation distribut…
On Localized Discrepancy for Domain Adaptation
Yuchen Zhang, Mingsheng Long, Jianmin Wang +1
We propose the discrepancy-based generalization theories for unsupervised domain adaptation. Previous theories introduced distribution discrepancies defined as the supremum over co…
Bridging Theory and Algorithm for Domain Adaptation
Yuchen Zhang, Tianle Liu, Mingsheng Long +1
This paper addresses the problem of unsupervised domain adaption from theoretical and algorithmic perspectives. Existing domain adaptation theories naturally imply minimax optimiza…
Defending against Whitebox Adversarial Attacks via Randomized Discretization
Yuchen Zhang, Percy Liang
Adversarial perturbations dramatically decrease the accuracy of state-of-the-art image classifiers. In this paper, we propose and analyze a simple and computationally efficient def…
A Hitting Time Analysis of Stochastic Gradient Langevin Dynamics
Yuchen Zhang, Percy Liang, Moses Charikar
We study the Stochastic Gradient Langevin Dynamics (SGLD) algorithm for non-convex optimization. The algorithm performs stochastic gradient descent, where in each step it injects a…
Convexified Convolutional Neural Networks
Yuchen Zhang, Percy Liang, Martin J. Wainwright
We describe the class of convexified convolutional neural networks (CCNNs), which capture the parameter sharing of convolutional neural networks in a convex manner. By representing…
Learning Halfspaces and Neural Networks with Random Initialization
Yuchen Zhang, Jason D. Lee, Martin J. Wainwright +1
We study non-convex empirical risk minimization for learning halfspaces and neural networks. For loss functions that are -Lipschitz continuous, we present algorithms to learn ha…
-regularized Neural Networks are Improperly Learnable in Polynomial Time
Yuchen Zhang, Jason D. Lee, Michael I. Jordan
We study the improper learning of multi-layer neural networks. Suppose that the neural network to be learned has hidden layers and that the -norm of the incoming weight…
Splash: User-friendly Programming Interface for Parallelizing Stochastic Algorithms
Yuchen Zhang, Michael I. Jordan
Stochastic algorithms are efficient approaches to solving machine learning and optimization problems. In this paper, we propose a general framework called Splash for parallelizing…