activity
20172021
most citedOnline Continuous Submodular Maximization: From Full-Information to Bandit Feedback

20 citations · 51 across the 9 of their papers we have counts for

collaborators
Showing cs.LGShow all

12 papers · 1 filter

cs.LG20212 cited

Feature Cross Search via Submodular Optimization

Lin Chen, Hossein Esfandiari, Gang Fu +2

In this paper, we study feature cross search as a fundamental primitive in feature engineering. The importance of feature cross search especially for the linear model has been know…

cs.LG20214 cited

Infinite-Horizon Offline Reinforcement Learning with Linear Function Approximation: Curse of Dimensionality and Algorithm

Lin Chen, Bruno Scherrer, Peter L. Bartlett

In this paper, we investigate the sample complexity of policy evaluation in infinite-horizon offline reinforcement learning (also known as the off-policy evaluation problem) with l…

cs.LG2020

Deep Neural Tangent Kernel and Laplace Kernel Have the Same RKHS

Lin Chen, Sheng Xu

We prove that the reproducing kernel Hilbert spaces (RKHS) of a deep neural tangent kernel and the Laplace kernel include the same set of functions, when both kernels are restricte…

cs.LG2020

The Curious Case of Adversarially Robust Models: More Data Can Help, Double Descend, or Hurt Generalization

Yifei Min, Lin Chen, Amin Karbasi

Adversarial training has shown its ability in producing models that are robust to perturbations on the input data, but usually at the expense of decrease in the standard accuracy.…

cs.LG2020

More Data Can Expand the Generalization Gap Between Adversarially Robust and Standard Models

Lin Chen, Yifei Min, Mingrui Zhang +1

Despite remarkable success in practice, modern machine learning models have been found to be susceptible to adversarial attacks that make human-imperceptible perturbations to the d…

cs.LG201920 cited

Online Continuous Submodular Maximization: From Full-Information to Bandit Feedback

Mingrui Zhang, Lin Chen, Hamed Hassani +1

In this paper, we propose three online algorithms for submodular maximisation. The first one, Mono-Frank-Wolfe, reduces the number of per-function gradient evaluations from $T^{1/2…