
MetaDistiller: Network SelfBoosting via MetaLearned TopDown Distillation
Knowledge Distillation (KD) has been one of the most popular methods to...
read it

On ℓ_pnorm Robustness of Ensemble Stumps and Trees
Recent papers have demonstrated that ensemble stumps and trees could be ...
read it

Improving the Speed and Quality of GAN by Adversarial Training
Generative adversarial networks (GAN) have shown remarkable results in i...
read it

Defense against Adversarial Attacks in NLP via Dirichlet Neighborhood Ensemble
Despite neural networks have achieved prominent performance on many natu...
read it

DrNAS: Dirichlet Neural Architecture Search
This paper proposes a novel differentiable architecture search method by...
read it

The Limit of the Batch Size
Largebatch training is an efficient approach for current distributed de...
read it

Provably Robust Metric Learning
Metric learning is an important family of algorithms for classification ...
read it

An Efficient Algorithm For Generalized Linear Bandit: Online Stochastic Gradient Descent and Thompson Sampling
We consider the contextual bandit problem, where a player sequentially m...
read it

Evaluations and Methods for Explanation through Robustness Analysis
Among multiple ways of interpreting a machine learning model, measuring ...
read it

Spanning Attack: Reinforce Blackbox Attacks with Unlabeled Data
Adversarial blackbox attacks aim to craft adversarial perturbations by ...
read it

Improved Adversarial Training via Learned Optimizer
Adversarial attack has recently become a tremendous threat to deep learn...
read it

Robust Deep Reinforcement Learning against Adversarial Perturbations on Observations
Deep Reinforcement Learning (DRL) is vulnerable to small adversarial per...
read it

Learning to Encode Position for Transformer with Continuous Dynamical Model
We introduce a new way of learning to encode position information for no...
read it

Automatic Perturbation Analysis on General Computational Graphs
Linear relaxation based perturbation analysis for neural networks, which...
read it

CAT: Customized Adversarial Training for Improved Robustness
Adversarial training has become one of the most effective methods for im...
read it

Robustness Verification for Transformers
Robustness verification that aims to formally certify the prediction beh...
read it

Multiscale Nonstationary Stochastic Bandits
Classic contextual bandit algorithms for linear models, such as LinUCB, ...
read it

Stabilizing Differentiable Architecture Search via Perturbationbased Regularization
Differentiable architecture search (DARTS) is a prevailing NAS solution ...
read it

MACER: Attackfree and Scalable Robust Training via Maximizing Certified Radius
Adversarial training is one of the most popular ways to learn robust mod...
read it

GraphDefense: Towards Robust Graph Convolutional Networks
In this paper, we study the robustness of graph convolutional networks (...
read it

Enhancing Certifiable Robustness via a Deep Model Ensemble
We propose an algorithm to enhance certified robustness of a deep model ...
read it

A Unified Framework for Data Poisoning Attack to Graphbased Semisupervised Learning
In this paper, we proposed a general framework for data poisoning attack...
read it

Learning to Learn by ZerothOrder Oracle
In the learning to learn (L2L) framework, we cast the design of optimiza...
read it

ElasticInfoGAN: Unsupervised Disentangled Representation Learning in Imbalanced Data
We propose a novel unsupervised generative model, ElasticInfoGAN, that ...
read it

SignOPT: A QueryEfficient Hardlabel Adversarial Attack
We study the most practical problem setup for evaluating adversarial rob...
read it

Toward Finding The Global Optimal of Adversarial Examples
Current machine learning models are vulnerable to adversarial examples (...
read it

Natural Adversarial Sentence Generation with Gradientbased Perturbation
This work proposes a novel algorithm to generate natural language advers...
read it

Temporal Collaborative Ranking Via Personalized Transformer
The collaborative ranking problem has been an important open research qu...
read it

VisualBERT: A Simple and Performant Baseline for Vision and Language
We propose VisualBERT, a simple and flexible framework for modeling a br...
read it

Convergence of Adversarial Training in Overparametrized Networks
Neural networks are vulnerable to adversarial examples, i.e. inputs that...
read it

Towards Stable and Efficient Training of Verifiably Robust Neural Networks
Training neural networks with verifiable robustness guarantees is challe...
read it

Evaluating the Robustness of Nearest Neighbor Classifiers: A PrimalDual Perspective
We study the problem of computing the minimum adversarial perturbation o...
read it

Robustness Verification of Treebased Models
We study the robustness verification problem for treebased models, incl...
read it

MLLOO: Detecting Adversarial Examples with Feature Attribution
Deep neural networks obtain stateoftheart performance on a series of ...
read it

Neural SDE: Stabilizing Neural ODE Networks with Stochastic Noise
Neural Ordinary Differential Equation (Neural ODE) has been proposed as ...
read it

Graph DNA: Deep Neighborhood Aware Graph Encoding for Collaborative Filtering
In this paper, we consider recommender systems with side information in ...
read it

Stochastic Shared Embeddings: Datadriven Regularization of Embedding Layers
In deep neural nets, lower level embedding layers account for a large po...
read it

ClusterGCN: An Efficient Algorithm for Training Deep and Large Graph Convolutional Networks
Graph convolutional network (GCN) has been successfully applied to many ...
read it

Evaluating Robustness of Deep Image SuperResolution against Adversarial Attacks
Singleimage superresolution aims to generate a highresolution version...
read it

Reducing BERT PreTraining Time from 3 Days to 76 Minutes
Largebatch training is key to speeding up deep neural network training ...
read it

Efficient Contextual Representation Learning Without Softmax Layer
Contextual representation models have achieved great success in improvin...
read it

Robust Decision Trees Against Adversarial Examples
Although adversarial examples and model robustness have been extensively...
read it

A Convex Relaxation Barrier to Tight Robustness Verification of Neural Networks
Verification of neural networks enables us to gauge their robustness aga...
read it

A Convex Relaxation Barrier to Tight Robust Verification of Neural Networks
Verification of neural networks enables us to gauge their robustness aga...
read it

LargeBatch Training for LSTM and Beyond
Largebatch training approaches have enabled researchers to utilize larg...
read it

The Limitations of Adversarial Training and the BlindSpot Attack
The adversarial training procedure proposed by Madry et al. (2018) is on...
read it

Optimal Transport Classifier: Defending Against Adversarial Attacks by Regularized Deep Embedding
Recent studies have demonstrated the vulnerability of deep convolutional...
read it

Blockwise Partitioning for Extreme Multilabel Classification
Extreme multilabel classification aims to learn a classifier that annot...
read it

Efficient Neural Network Robustness Certification with General Activation Functions
Finding minimum distortion of adversarial examples and thus certifying r...
read it

Learning to Screen for Fast Softmax Inference on Large Vocabulary Neural Networks
Neural language models have been widely used in various NLP tasks, inclu...
read it
ChoJui Hsieh
is this you? claim profile
Assistant professor of Computer Science and Statistics at UC Davis