activity
20172022
most citedNeural tangent kernels, transportation mappings, and universal approximation

10 citations · 28 across the 6 of their papers we have counts for

collaborators

12 papers

cs.LG2022

Agnostic Learnability of Halfspaces via Logistic Loss

Ziwei Ji, Kwangjun Ahn, Pranjal Awasthi +2

We investigate approximation guarantees provided by logistic regression for the fundamental problem of agnostic learning of homogeneous halfspaces. Previously, for a certain broad…

cs.LG20212 cited

Fast Margin Maximization via Dual Acceleration

Ziwei Ji, Nathan Srebro, Matus Telgarsky

We present and analyze a momentum-based gradient method for training linear classifiers with an exponentially-tailed loss (e.g., the exponential or logistic loss), which maximizes…

cs.LG20219 cited

Early-stopped neural networks are consistent

Ziwei Ji, Justin D. Li, Matus Telgarsky

This work studies the behavior of shallow ReLU networks trained with the logistic loss via gradient descent on binary classification data where the underlying data distribution is…

cs.LG20203 cited

Gradient descent follows the regularization path for general losses

Ziwei Ji, Miroslav Dudík, Robert E. Schapire +1

Recent work across many machine learning disciplines has highlighted that standard descent methods, even without explicit regularization, do not merely minimize the training error,…

cs.LG2020

Directional convergence and alignment in deep learning

Ziwei Ji, Matus Telgarsky

In this paper, we show that although the minimizers of cross-entropy and related classification losses are off at infinity, network weights learned by gradient flow converge in dir…

cs.LG201910 cited

Neural tangent kernels, transportation mappings, and universal approximation

Ziwei Ji, Matus Telgarsky, Ruicheng Xian

This paper establishes rates of universal approximation for the shallow neural tangent kernel (NTK): network weights are only allowed microscopic changes from random initialization…