518 citations · 1.3k across the 51 of their papers we have counts for
10 papers · 1 filter
Label-Aware Neural Tangent Kernel: Toward Better Generalization and Local Elasticity
Shuxiao Chen, Hangfeng He, Weijie J. Su
As a popular approach to modeling the dynamics of training overparametrized neural networks (NNs), the neural tangent kernels (NTK) are known to fall behind real-world NNs in gener…
Towards Understanding the Dynamics of the First-Order Adversaries
Zhun Deng, Hangfeng He, Jiaoyang Huang +1
An acknowledged weakness of neural networks is their vulnerability to adversarial perturbations to the inputs. To improve the robustness of these models, one of the most popular de…
Toward Better Generalization Bounds with Locally Elastic Stability
Zhun Deng, Hangfeng He, Weijie J. Su
Algorithmic stability is a key characteristic to ensure the generalization ability of a learning algorithm. Among different notions of stability, \emph{uniform stability} is arguab…
Precise High-Dimensional Asymptotics for Quantifying Heterogeneous Transfers
Fan Yang, Hongyang R. Zhang, Sen Wu +2
The problem of learning one task using samples from another task is central to transfer learning. In this paper, we focus on answering the following question: when does combining t…
Benign Overfitting and Noisy Features
Zhu Li, Weijie Su, Dino Sejdinovic
Modern machine learning often operates in the regime where the number of parameters is much higher than the number of data points, with zero training loss and yet good generalizati…
A Power Analysis for Model-X Knockoffs with -Regularized Statistics
Asaf Weinstein, Weijie J. Su, Małgorzata Bogdan +2
Variable selection properties of procedures utilizing penalized-likelihood estimates is a central topic in the study of high dimensional linear regression problems. Existing litera…
The Complete Lasso Tradeoff Diagram
Hua Wang, Yachong Yang, Zhiqi Bu +1
A fundamental problem in the high-dimensional regression is to understand the tradeoff between type I and type II errors or, equivalently, false discovery rate (FDR) and power in v…
The Price of Competition: Effect Size Heterogeneity Matters in High Dimensions
Hua Wang, Yachong Yang, Weijie J. Su
In high-dimensional sparse regression, would increasing the signal-to-noise ratio while fixing the sparsity level always lead to better model selection? For high-dimensional sparse…
On Learning Rates and Schrödinger Operators
Bin Shi, Weijie J. Su, Michael I. Jordan
The learning rate is perhaps the single most important parameter in the training of neural networks and, more broadly, in stochastic (nonconvex) optimization. Accordingly, there ar…
Sharp Composition Bounds for Gaussian Differential Privacy via Edgeworth Expansion
Qinqing Zheng, Jinshuo Dong, Qi Long +1
Datasets containing sensitive information are often sequentially analyzed by many algorithms. This raises a fundamental question in differential privacy regarding how the overall p…