1.3k citations · 1.7k across the 19 of their papers we have counts for
19 papers
Stochastic Optimization for Non-convex Problem with Inexact Hessian Matrix, Gradient, and Function
Liu Liu, Xuanqing Liu, Cho-Jui Hsieh +1
Trust-region (TR) and adaptive regularization using cubics (ARC) have proven to have some very appealing theoretical properties for non-convex optimization by concurrently computin…
LLMs Can Understand Encrypted Prompt: Towards Privacy-Computing Friendly Transformers
Xuanqi Liu, Zhuotao Liu
The community explored to build private inference frameworks for transformer-based large language models (LLMs) in a server-client setting, where the server holds the model paramet…
How much progress have we made in neural network training? A New Evaluation Protocol for Benchmarking Optimizers
Yuanhao Xiong, Xuanqing Liu, Li-Cheng Lan +3
Many optimizers have been proposed for training deep neural networks, and they often have multiple hyperparameters, which make it tricky to benchmark their performance. In this wor…
Improving the Speed and Quality of GAN by Adversarial Training
Jiachen Zhong, Xuanqing Liu, Cho-Jui Hsieh
Generative adversarial networks (GAN) have shown remarkable results in image generation tasks. High fidelity class-conditional GAN methods often rely on stabilization techniques by…
Provably Robust Metric Learning
Lu Wang, Xuanqing Liu, Jinfeng Yi +2
Metric learning is an important family of algorithms for classification and similarity search, but the robustness of learned metrics against small adversarial perturbations is less…
Evaluations and Methods for Explanation through Robustness Analysis
Cheng-Yu Hsieh, Chih-Kuan Yeh, Xuanqing Liu +4
Feature based explanations, that provide importance of each feature towards the model prediction, is arguably one of the most intuitive ways to explain a model. In this paper, we e…
Learning to Encode Position for Transformer with Continuous Dynamical Model
Xuanqing Liu, Hsiang-Fu Yu, Inderjit Dhillon +1
We introduce a new way of learning to encode position information for non-recurrent models, such as Transformer models. Unlike RNN and LSTM, which contain inductive bias by loading…
Gradient Boosting Neural Networks: GrowNet
Sarkhan Badirli, Xuanqing Liu, Zhengming Xing +3
A novel gradient boosting framework is proposed where shallow neural networks are employed as ``weak learners''. General loss functions are considered under this unified framework…
GraphDefense: Towards Robust Graph Convolutional Networks
Xiaoyun Wang, Xuanqing Liu, Cho-Jui Hsieh
In this paper, we study the robustness of graph convolutional networks (GCNs). Despite the good performance of GCNs on graph semi-supervised learning tasks, previous works have sho…
A Unified Framework for Data Poisoning Attack to Graph-based Semi-supervised Learning
Xuanqing Liu, Si Si, Xiaojin Zhu +2
In this paper, we proposed a general framework for data poisoning attacks to graph-based semi-supervised learning (G-SSL). In this framework, we first unify different tasks, goals,…
Evaluating the Robustness of Nearest Neighbor Classifiers: A Primal-Dual Perspective
Lu Wang, Xuanqing Liu, Jinfeng Yi +2
We study the problem of computing the minimum adversarial perturbation of the Nearest Neighbor (NN) classifiers. Previous attempts either conduct attacks on continuous approximatio…
Neural SDE: Stabilizing Neural ODE Networks with Stochastic Noise
Xuanqing Liu, Tesi Xiao, Si Si +3
Neural Ordinary Differential Equation (Neural ODE) has been proposed as a continuous approximation to the ResNet architecture. Some commonly used regularization mechanisms in discr…
Cluster-GCN: An Efficient Algorithm for Training Deep and Large Graph Convolutional Networks
Wei-Lin Chiang, Xuanqing Liu, Si Si +3
Graph convolutional network (GCN) has been successfully applied to many graph-based applications; however, training a large-scale GCN remains challenging. Current SGD-based algorit…
Adv-BNN: Improved Adversarial Defense through Robust Bayesian Neural Network
Xuanqing Liu, Yao Li, Chongruo Wu +1
We present a new algorithm to train a robust neural network against adversarial attacks. Our algorithm is motivated by the following two ideas. First, although recent work has demo…
Stochastic Second-order Methods for Non-convex Optimization with Inexact Hessian and Gradient
Liu Liu, Xuanqing Liu, Cho-Jui Hsieh +1
Trust region and cubic regularization methods have demonstrated good performance in small scale non-convex optimization, showing the ability to escape from saddle points. Each iter…
Fast Variance Reduction Method with Stochastic Batch Size
Xuanqing Liu, Cho-Jui Hsieh
In this paper we study a family of variance reduction methods with randomized batch size---at each step, the algorithm first randomly chooses the batch size and then selects a batc…
Rob-GAN: Generator, Discriminator, and Adversarial Attacker
Xuanqing Liu, Cho-Jui Hsieh
We study two important concepts in adversarial deep learning---adversarial training and generative adversarial network (GAN). Adversarial training is the technique used to improve…
Towards Robust Neural Networks via Random Self-ensemble
Xuanqing Liu, Minhao Cheng, Huan Zhang +1
Recent studies have revealed the vulnerability of deep neural networks: A small adversarial perturbation that is imperceptible to human can easily make a well-trained deep neural n…
An inexact subsampled proximal Newton-type method for large-scale machine learning
Xuanqing Liu, Cho-Jui Hsieh, Jason D. Lee +1
We propose a fast proximal Newton-type algorithm for minimizing regularized finite sums that returns an -suboptimal point in $\tilde{\mathcal{O}}(d(n + \sqrt{κd})\log(\frac{1}ε)…