C
Cho-Jui Hsieh
Researcher at University of California, Los Angeles
Publications - 355
Citations - 29087
Cho-Jui Hsieh is an academic researcher from University of California, Los Angeles. The author has contributed to research in topics: Robustness (computer science) & Computer science. The author has an hindex of 60, co-authored 301 publications receiving 22410 citations. Previous affiliations of Cho-Jui Hsieh include Amazon.com & University of California, Davis.
Papers
More filters
Journal ArticleDOI
Supracellular Measurement of Spatially Varying Mechanical Heterogeneities in Live Monolayers.
Alexandra Bermudez,Zachary Gonzalez,Bao Zhao,Ethan Salter,Xuanqing Liu,Leixin Ma,Mohammad Khalid Jawed,Cho-Jui Hsieh,N.-Y. Lin +8 more
TL;DR: In this article , the authors quantified the heterogeneous deformation of a slightly stretched cell layer and converted the measured strain fields into an effective modulus field using an AI inference.
Journal ArticleDOI
Red Teaming Language Model Detectors with Language Models
TL;DR: In this article , the authors systematically test the reliability of the existing machine-generated text detection algorithms by designing two types of attack strategies to fool the detectors: replacing words with their synonyms based on the context; and altering the writing style of generated text.
Posted Content
Label Disentanglement in Partition-based Extreme Multilabel Classification
TL;DR: In this article, the label assignment problem in partition-based XMC can be formulated as an optimization problem, with the objective of maximizing precision rates, which leads to an efficient algorithm to form flexible and overlapped label clusters, and a method that can alternatively optimizes the cluster assignments and the model parameters.
Proceedings Article
Evaluations and Methods for Explanation through Robustness Analysis
Cheng-Yu Hsieh,Chih-Kuan Yeh,Xuanqing Liu,Pradeep Ravikumar,Seungyeon Kim,Sanjiv Kumar,Cho-Jui Hsieh +6 more
TL;DR: In this article, a set of evaluation criteria for feature-based explanations by robustness analysis is established, in contrast to existing evaluations which require us to specify some way to ''remove'' features that could inevitably introduce biases and artifacts, they make use of the subtler notion of smaller adversarial perturbations.
Posted Content
Robust Stochastic Linear Contextual Bandits Under Adversarial Attacks.
TL;DR: In this article, the authors proposed a robust bandit algorithm for stochastic linear contextual bandit under a fully adaptive and omniscient attack, which does not need any information about the attack budget or the particular form of the attack.