activity
20122022
most citedScalable Matrix-valued Kernel Learning for High-dimensional Nonlinear Multivariate Regression and Granger Causality

11 citations · 25 across the 6 of their papers we have counts for

collaborators

11 papers

cs.LG20221 cited

Directed Graph Auto-Encoders

Georgios Kollias, Vasileios Kalantzis, Tsuyoshi Idé +2

We introduce a new class of auto-encoders for directed graphs, motivated by a direct extension of the Weisfeiler-Leman algorithm to pairs of node labels. The proposed model learns…

cs.LG2020

A Revision of Neural Tangent Kernel-based Approaches for Neural Networks

Kyung-Su Kim, Aurélie C. Lozano, Eunho Yang

Recent theoretical works based on the neural tangent kernel (NTK) have shed light on the optimization and generalization of over-parameterized networks, and partially bridge the ga…

cs.LG20207 cited

A General Family of Stochastic Proximal Gradient Methods for Deep Learning

Jihun Yun, Aurelie C. Lozano, Eunho Yang

We study the training of regularized neural networks where the regularizer can be non-smooth and non-convex. We propose a unified framework for stochastic proximal gradient descent…

cs.LG20192 cited

Stochastic Gradient Methods with Block Diagonal Matrix Adaptation

Jihun Yun, Aurelie C. Lozano, Eunho Yang

Adaptive gradient approaches that automatically adjust the learning rate on a per-feature basis have been very popular for training deep networks. This rich class of algorithms inc…

cs.LG2018

On Extensions of CLEVER: A Neural Network Robustness Evaluation Algorithm

Tsui-Wei Weng, Huan Zhang, Pin-Yu Chen +3

CLEVER (Cross-Lipschitz Extreme Value for nEtwork Robustness) is an Extreme Value Theory (EVT) based robustness score for large-scale deep neural networks (DNNs). In this paper, we…

math.ST2018

M-estimation with the Trimmed l1 Penalty

Jihun Yun, Peng Zheng, Eunho Yang +2

We study high-dimensional estimators with the trimmed penalty, which leaves the largest parameter entries penalty-free. While optimization techniques for this nonconve…