3 papers
cs.LG2024
Feature compression is the root cause of adversarial fragility in neural network classifiers
Jingchao Gao, Ziqing Lu, Raghu Mudumbai +6
In this paper, we uniquely study the adversarial robustness of deep neural networks (NN) for classification tasks against that of optimal classifiers. We look at the smallest magni…
eess.SP2022
Optimal Compression for Minimizing Classification Error Probability: an Information-Theoretic Approach
Jingchao Gao, Ao Tang, Weiyu Xu
We formulate the problem of performing optimal data compression under the constraints that compressed data can be used for accurate classification in machine learning. We show that…
cs.IT2018
Outlier Detection using Generative Models with Theoretical Performance Guarantees
Jirong Yi, Anh Duc Le, Tianming Wang +2
This paper considers the problem of recovering signals from compressed measurements contaminated with sparse outliers, which has arisen in many applications. In this paper, we prop…