activity
20192025
most citedInformative Dropout for Robust Representation Learning: A Shape-bias Perspective

45 citations · 69 across the 5 of their papers we have counts for

collaborators

6 papers

cs.LG20222 cited

Generative Augmented Flow Networks

Ling Pan, Dinghuai Zhang, Aaron Courville +2

The Generative Flow Network is a probabilistic framework where an agent learns a stochastic policy for object generation, such that the probability of generating an object is propo…

cs.LG202116 cited

Can Subnetwork Structure be the Key to Out-of-Distribution Generalization?

Dinghuai Zhang, Kartik Ahuja, Yilun Xu +2

Can models with particular structure avoid being biased towards spurious correlation in out-of-distribution (OOD) generalization? Peters et al. (2016) provides a positive answer fo…

stat.ML2020

Neural Approximate Sufficient Statistics for Implicit Models

Yanzhi Chen, Dinghuai Zhang, Michael Gutmann +2

We consider the fundamental problem of how to automatically construct summary statistics for implicit generative models where the evaluation of the likelihood function is intractab…

cs.LG202045 cited

Informative Dropout for Robust Representation Learning: A Shape-bias Perspective

Baifeng Shi, Dinghuai Zhang, Qi Dai +3

Convolutional Neural Networks (CNNs) are known to rely more on local texture rather than global shape when making decisions. Recent work also indicates a close relationship between…

cs.LG2020

Black-Box Certification with Randomized Smoothing: A Functional Optimization Based Framework

Dinghuai Zhang, Mao Ye, Chengyue Gong +2

Randomized classifiers have been shown to provide a promising approach for achieving certified robustness against adversarial attacks in deep learning. However, most existing metho…

stat.ML2019

You Only Propagate Once: Accelerating Adversarial Training via Maximal Principle

Dinghuai Zhang, Tianyuan Zhang, Yiping Lu +2

Deep learning achieves state-of-the-art results in many tasks in computer vision and natural language processing. However, recent works have shown that deep networks can be vulnera…