no code implementations • NeurIPS 2008 • Jun Zhu, Eric P. Xing, Bo Zhang
Learning graphical models with hidden variables can offer semantic insights to complex data and lead to salient structured predictors without relying on expensive, sometime unattainable fully annotated training data.
no code implementations • NeurIPS 2010 • Ni Lao, Jun Zhu, Liu Liu, Yandong Liu, William W. Cohen
Markov networks (MNs) can incorporate arbitrarily complex features in modeling relational data.
no code implementations • NeurIPS 2010 • Jun Zhu, Li-Jia Li, Li Fei-Fei, Eric P. Xing
This paper presents a joint max-margin and max-likelihood learning method for upstream scene understanding models, in which latent topic discovery and prediction model estimation are closely coupled and well-balanced.
no code implementations • NeurIPS 2010 • Seunghak Lee, Jun Zhu, Eric P. Xing
To understand the relationship between genomic variations among population and complex diseases, it is essential to detect eQTLs which are associated with phenotypic effects.
no code implementations • NeurIPS 2010 • Ning Chen, Jun Zhu, Eric P. Xing
Learning from multi-view data is important in many applications, such as image classification and annotation.
no code implementations • NeurIPS 2011 • Jun Zhu, Ning Chen, Eric P. Xing
Unlike existing nonparametric Bayesian models, which rely solely on specially conceived priors to incorporate domain knowledge for discovering improved latent representations, we study nonparametric Bayesian inference with regularization on the desired posterior distributions.
no code implementations • 5 Oct 2012 • Jun Zhu, Ning Chen, Eric P. Xing
When the regularization is induced from a linear operator on the posterior distributions, such as the expectation operator, we present a general convex-analysis theorem to characterize the solution of RegBayes.
no code implementations • NeurIPS 2012 • Qixia Jiang, Jun Zhu, Maosong Sun, Eric P. Xing
An effective strategy to exploit the supervising side information for discovering predictive topic representations is to impose discriminative constraints induced by such information on the posterior distributions under a topic model.
no code implementations • ACL 2013 • Jun Zhu, Xun Zheng, Bo Zhang
Supervised topic models with a logistic likelihood have two issues that potentially limit their practical use: 1) response variables are usually over-weighted by document word counts; and 2) existing variational inference methods make strict mean-field assumptions.
no code implementations • 9 Oct 2013 • Ning Chen, Jun Zhu, Fei Xia, Bo Zhang
Many scientific and engineering fields involve analyzing network data.
no code implementations • 10 Oct 2013 • Jun Zhu, Ning Chen, Hugh Perkins, Bo Zhang
Gibbs max-margin supervised topic models minimize an expected margin loss, which is an upper bound of the existing margin loss derived from an expected prediction rule.
no code implementations • NeurIPS 2013 • Jianfei Chen, Jun Zhu, Zi Wang, Xun Zheng, Bo Zhang
Logistic-normal topic models can effectively discover correlation structures among latent topics.
no code implementations • 12 Dec 2013 • Tianlin Shi, Jun Zhu
Online Passive-Aggressive (PA) learning is an effective framework for performing max-margin online learning.
no code implementations • 16 Apr 2014 • Ning Chen, Jun Zhu, Jianfei Chen, Bo Zhang
To deal with the intractable expectation of the non-smooth hinge loss under corrupting distributions, we develop an iteratively re-weighted least square (IRLS) algorithm by exploring data augmentation techniques.
no code implementations • 28 Jun 2014 • Ni Lao, Jun Zhu
We prove that the gradient of candidate features can be represented solely as a function of signals and errors, and that CFI is an efficient approximation of gradient-based evaluation methods.
no code implementations • 24 Nov 2014 • Jun Zhu, Jianfei Chen, Wen-Bo Hu, Bo Zhang
Explosive growth in data and availability of cheap computing resources have sparked increasing interest in Big learning, an emerging subfield that studies scalable machine learning algorithms, systems, and applications with Big Data.
no code implementations • NeurIPS 2014 • Minjie Xu, Balaji Lakshminarayanan, Yee Whye Teh, Jun Zhu, Bo Zhang
We propose a distributed Markov chain Monte Carlo (MCMC) inference algorithm for large scale Bayesian posterior simulation.
no code implementations • NeurIPS 2014 • Changyou Chen, Jun Zhu, Xinhua Zhang
We present max-margin Bayesian clustering (BMC), a general and robust framework that incorporates the max-margin criterion into Bayesian clustering models, as well as two concrete models of BMC to demonstrate its flexibility and effectiveness in dealing with different clustering tasks.
no code implementations • NeurIPS 2014 • Yining Wang, Jun Zhu
Supervised topic models simultaneously model the latent topic structure of large collections of documents and a response variable associated with each document.
no code implementations • NeurIPS 2014 • Jun Zhu, Junhua Mao, Alan L. Yuille
We propose a novel learning algorithm called \emph{expectation loss SVM} (e-SVM) that is devoted to the problems where only the ``positiveness" instead of a binary label of each training sample is available.
2 code implementations • NeurIPS 2015 • Chongxuan Li, Jun Zhu, Tianlin Shi, Bo Zhang
Deep generative models (DGMs) are effective on learning multilayered representations of complex data and performing inference of input data by exploring the generative ability.
no code implementations • 27 Apr 2015 • Wenbo Hu, Jun Zhu, Bo Zhang
Bayesian max-margin models have shown superiority in various practical applications, such as text categorization, collaborative prediction, social network link prediction and crowdsourcing, and they conjoin the flexibility of Bayesian modeling and predictive strengths of max-margin learning.
no code implementations • 10 May 2015 • Renjie Liao, Jianping Shi, Ziyang Ma, Jun Zhu, Jiaya Jia
Metric learning aims to embed one metric space into another to benefit tasks like classification and clustering.
no code implementations • 15 Jun 2015 • Chao Du, Jun Zhu, Bo Zhang
We present doubly stochastic gradient MCMC, a simple and generic method for (approximate) Bayesian inference of deep generative models (DGMs) in a collapsed continuous parameter space.
no code implementations • 10 Aug 2015 • Ning Chen, Jun Zhu, Jianfei Chen, Ting Chen
Empirical results on several real datasets demonstrate the effectiveness of dropout training on significantly boosting the classification accuracy of both linear and nonlinear SVMs.
1 code implementation • EMNLP 2015 • Shaohua Li, Jun Zhu, Chunyan Miao
Most existing word embedding methods can be categorized into Neural Embedding Models and Matrix Factorization (MF)-based methods.
no code implementations • 17 Aug 2015 • Fangting Xia, Jun Zhu, Peng Wang, Alan Yuille
Parsing human body into semantic regions is crucial to human-centric analysis.
no code implementations • 29 Oct 2015 • Jianfei Chen, Kaiwei Li, Jun Zhu, WenGuang Chen
We then develop WarpLDA, an LDA sampler which achieves both the best O(1) time complexity per token and the best O(K) scope of random access.
no code implementations • 23 Nov 2015 • Jun Zhu, Xianjie Chen, Alan L. Yuille
In this paper, we propose a deep part-based model (DeePM) for symbiotic object detection and semantic part localization.
no code implementations • NeurIPS 2015 • Tian Tian, Jun Zhu
Learning-from-crowds aims to design proper aggregation strategies to infer the unknown true labels from the noisy labels provided by ordinary web workers.
no code implementations • 3 Dec 2015 • Jiaxin Shi, Jun Zhu
We present a new perspective on neural knowledge base (KB) embeddings, from which we build a framework that can model symbolic knowledge in the KB together with its learning process.
1 code implementation • 3 Dec 2015 • Yang Song, Jun Zhu
Bayesian matrix completion has been studied based on a low-rank matrix factorization formulation with promising results.
no code implementations • 7 Dec 2015 • Bei Chen, Jun Zhu, Nan Yang, Tian Tian, Ming Zhou, Bo Zhang
Modeling document structure is of great importance for discourse analysis and related applications.
no code implementations • 7 Dec 2015 • Bei Chen, Ning Chen, Jun Zhu, Jiaming Song, Bo Zhang
We present a discriminative nonparametric latent feature relational model (LFRM) for link prediction to automatically infer the dimensionality of latent features.
no code implementations • 24 Dec 2015 • Hugh Perkins, Minjie Xu, Jun Zhu, Bo Zhang
As one of the most popular classifiers, linear SVMs still have challenges in dealing with very large-scale problems, even though linear or sub-linear algorithms have been developed recently on single machines.
no code implementations • 6 Jan 2016 • Yang Gao, Jianfei Chen, Jun Zhu
Streaming variational Bayes (SVB) is successful in learning LDA models in an online manner.
no code implementations • 19 Feb 2016 • Yong Ren, Yining Wang, Jun Zhu
Spectral methods have been applied to learn unsupervised topic models, such as latent Dirichlet allocation (LDA), with provable guarantees.
1 code implementation • 19 Feb 2016 • Arnab Bhadury, Jianfei Chen, Jun Zhu, Shixia Liu
Dynamic topic models (DTMs) are very effective in discovering topics and capturing their evolution trends in time series data.
no code implementations • 24 Feb 2016 • Jun Zhu, Jiaming Song, Bei Chen
Our approach attempts to unite the ideas of max-margin learning and Bayesian nonparametrics to discover discriminative latent features for link prediction.
1 code implementation • 24 Feb 2016 • Chongxuan Li, Jun Zhu, Bo Zhang
Memory units have been widely used to enrich the capabilities of deep networks on capturing long-term dependencies in reasoning and prediction tasks, but little investigation exists on deep generative models (DGMs) which are good at inferring high-level invariant representations from unlabeled data.
no code implementations • 24 Apr 2016 • Mengchen Liu, Jiaxin Shi, Zhen Li, Chongxuan Li, Jun Zhu, Shixia Liu
Deep convolutional neural networks (CNNs) have achieved breakthrough performance in many pattern recognition tasks such as image classification.
1 code implementation • 9 Jun 2016 • Shaohua Li, Tat-Seng Chua, Jun Zhu, Chunyan Miao
Word embedding maps words into a low-dimensional continuous embedding space by exploiting the local word collocation patterns in a small context window.
no code implementations • 10 Jun 2016 • Shaohua Li, Jun Zhu, Chunyan Miao
PSDVec is a Python/Perl toolbox that learns word embeddings, i. e. the mapping of words in a natural language to continuous vectors which encode the semantic/syntactic regularities between the words.
no code implementations • NeurIPS 2016 • Yong Ren, Jialian Li, Yucen Luo, Jun Zhu
Maximum mean discrepancy (MMD) has been successfully applied to learn deep generative models for characterizing a joint distribution of variables via kernel mean embedding.
no code implementations • NeurIPS 2016 • Yang Song, Jun Zhu, Yong Ren
We propose a vector-valued regression problem whose solution is equivalent to the reproducing kernel Hilbert space (RKHS) embedding of the Bayesian posterior distribution.
no code implementations • 8 Oct 2016 • Kaiwei Li, Jianfei Chen, WenGuang Chen, Jun Zhu
Latent Dirichlet Allocation (LDA) is a popular tool for analyzing discrete count data such as text and images.
1 code implementation • 22 Nov 2016 • Chongxuan Li, Jun Zhu, Bo Zhang
Deep generative models (DGMs) are effective on learning multilayered representations of complex data and performing inference of input data by exploring the generative ability.
no code implementations • 29 Nov 2016 • Jingkang Yang, Haohan Wang, Jun Zhu, Eric P. Xing
In this paper, we propose an extension of State Space Model to work with different sources of information together with its learning and inference algorithms.
no code implementations • NeurIPS 2016 • Chang Liu, Jun Zhu, Yang song
We propose two stochastic gradient MCMC methods for sampling from Bayesian posterior distributions defined on Riemann manifolds with a known geodesic flow, e. g. hyperspheres.
no code implementations • 7 Dec 2016 • Binghong Chen, Jun Zhu
Group-Lasso (gLasso) identifies important explanatory factors in predicting the response variable by considering the grouping structure over input variables.
1 code implementation • 21 Dec 2016 • Chao Du, Chongxuan Li, Yin Zheng, Jun Zhu, Bo Zhang
Deep neural networks have shown promise in collaborative filtering (CF).
no code implementations • 4 Feb 2017 • Shixia Liu, Xiting Wang, Mengchen Liu, Jun Zhu
Interactive model analysis, the process of understanding, diagnosing, and refining a machine learning model with the help of interactive visualization, is very important for users to efficiently solve real-world artificial intelligence and data mining problems.
no code implementations • 23 Feb 2017 • Jianfei Chen, Jun Zhu, Jie Lu, Shixia Liu
Finally, we propose an efficient distributed implementation of PCGS through vectorization, pre-processing, and a careful design of the concurrent data structures and communication strategy.
1 code implementation • NeurIPS 2017 • Chongxuan Li, Kun Xu, Jun Zhu, Bo Zhang
Generative Adversarial Nets (GANs) have shown promise in image generation and semi-supervised learning (SSL).
no code implementations • CVPR 2017 • Yinpeng Dong, Hang Su, Jun Zhu, Bo Zhang
Interpretability of deep neural networks (DNNs) is essential since it enables users to understand the overall strengths and weaknesses of the models, conveys an understanding of how the models will behave in the future, and how to diagnose and correct potential problems.
no code implementations • ICLR 2018 • Jiaxin Shi, Shengyang Sun, Jun Zhu
Recent progress in variational inference has paid much attention to the flexibility of variational posteriors.
1 code implementation • NeurIPS 2018 • Tianyu Pang, Chao Du, Yinpeng Dong, Jun Zhu
Although the recent progress is substantial, deep learning methods can be vulnerable to the maliciously generated adversarial examples.
1 code implementation • 8 Jun 2017 • Yujie Wu, Lei Deng, Guoqi Li, Jun Zhu, Luping Shi
By simultaneously considering the layer-by-layer spatial domain (SD) and the timing-dependent temporal domain (TD) in the training phase, as well as an approximated derivative for the spike activity, we propose a spatio-temporal backpropagation (STBP) training framework without using any complicated technology.
1 code implementation • 28 Jun 2017 • Haosheng Zou, Kun Xu, Jialian Li, Jun Zhu
We took part in the YouTube-8M Video Understanding Challenge hosted on Kaggle, and achieved the 10th place within less than one month's time.
no code implementations • 25 Jul 2017 • Jianyu Wang, Cihang Xie, Zhishuai Zhang, Jun Zhu, Lingxi Xie, Alan Yuille
Our approach detects semantic parts by accumulating the confidence of local visual cues.
no code implementations • ICML 2017 • Yichi Zhou, Jialian Li, Jun Zhu
We study the problem on how to learn the pure Nash Equilibrium of a two-player zero-sum static game with random payoffs under unknown distributions via efficient payoff queries.
1 code implementation • 3 Aug 2017 • Yinpeng Dong, Renkun Ni, Jianguo Li, Yurong Chen, Jun Zhu, Hang Su
This procedure can greatly compensate the quantization error and thus yield better accuracy for low-bit DNNs.
no code implementations • ICML 2018 • Yichi Zhou, Jun Zhu, Jingwei Zhuo
Thompson sampling has impressive empirical performance for many multi-armed bandit problems.
no code implementations • 18 Aug 2017 • Yinpeng Dong, Hang Su, Jun Zhu, Fan Bao
We find that: (1) the neurons in DNNs do not truly detect semantic objects/parts, but respond to objects/parts only as recurrent discriminative patches; (2) deep visual representations are not robust distributed codes of visual concepts because the representations of adversarial images are largely not consistent with those of real images, although they have similar visual appearance, both of which are different from previous findings.
1 code implementation • 18 Sep 2017 • Jiaxin Shi, Jianfei Chen, Jun Zhu, Shengyang Sun, Yucen Luo, Yihong Gu, Yuhao Zhou
In this paper we introduce ZhuSuan, a python probabilistic programming library for Bayesian deep learning, which conjoins the complimentary advantages of Bayesian methods and deep learning.
7 code implementations • CVPR 2018 • Yinpeng Dong, Fangzhou Liao, Tianyu Pang, Hang Su, Jun Zhu, Xiaolin Hu, Jianguo Li
To further improve the success rates for black-box attacks, we apply momentum iterative algorithms to an ensemble of models, and show that the adversarially trained models with a strong defense ability are also vulnerable to our black-box attacks.
2 code implementations • ICML 2018 • Jianfei Chen, Jun Zhu, Le Song
Previous attempts on reducing the receptive field size by subsampling neighbors do not have a convergence guarantee, and their receptive field size per node is still in the order of hundreds.
1 code implementation • CVPR 2018 • Yucen Luo, Jun Zhu, Mengxi Li, Yong Ren, Bo Zhang
In SNTG, a graph is constructed based on the predictions of the teacher model, i. e., the implicit self-ensemble of models.
1 code implementation • NeurIPS 2017 • Zhijie Deng, Hao Zhang, Xiaodan Liang, Luona Yang, Shizhen Xu, Jun Zhu, Eric P. Xing
We study the problem of conditional generative modeling based on designated semantics or structures.
no code implementations • 13 Nov 2017 • Jianyu Wang, Zhishuai Zhang, Cihang Xie, Yuyin Zhou, Vittal Premachandran, Jun Zhu, Lingxi Xie, Alan Yuille
We use clustering algorithms to study the population activities of the features and extract a set of visual concepts which we show are visually tight and correspond to semantic parts of vehicles.
no code implementations • ICML 2018 • Jingwei Zhuo, Chang Liu, Jiaxin Shi, Jun Zhu, Ning Chen, Bo Zhang
Stein variational gradient descent (SVGD) is a recently proposed particle-based Bayesian inference method, which has attracted a lot of interest due to its remarkable approximation ability and particle efficiency compared to traditional variational inference and Markov Chain Monte Carlo methods.
no code implementations • 23 Nov 2017 • Pengtao Xie, Jun Zhu, Eric P. Xing
We also extend our approach to "diversify" Bayesian nonparametric models where the number of components is infinite.
1 code implementation • 30 Nov 2017 • Chang Liu, Jun Zhu
The benefits are two-folds: (i) for inference tasks in Euclidean spaces, RSVGD has the advantage over SVGD of utilizing information geometry, and (ii) for inference tasks on Riemann manifolds, RSVGD brings the unique advantages of SVGD to the Riemannian world.
no code implementations • NeurIPS 2017 • Jianfei Chen, Chongxuan Li, Yizhong Ru, Jun Zhu
In this paper, we propose population matching discrepancy (PMD) for estimating the distribution distance based on samples, as well as an algorithm to learn the parameters of the distributions using PMD as an objective.
no code implementations • 6 Dec 2017 • Danyang Sun, Tongzheng Ren, Chongxun Li, Hang Su, Jun Zhu
Automatically writing stylized Chinese characters is an attractive yet challenging task due to its wide applicabilities.
no code implementations • 7 Dec 2017 • Jianqiao Wangni, Jingwei Zhuo, Jun Zhu
Since the algorithm consumes a major computation cost in the testing phase, we propose a novel teacher-learner framework of learning computation-efficient kernel embeddings from specific data.
2 code implementations • CVPR 2018 • Fangzhou Liao, Ming Liang, Yinpeng Dong, Tianyu Pang, Xiaolin Hu, Jun Zhu
First, with HGD as a defense, the target model is more robust to either white-box or black-box adversarial attacks.
2 code implementations • 14 Dec 2017 • Jian Wu, Changran Hu, Yulong Wang, Xiaolin Hu, Jun Zhu
In this paper, we present a hierarchical recurrent neural network for melody generation, which consists of three Long-Short-Term-Memory (LSTM) subnetworks working in a coarse-to-fine manner along time.
Sound Multimedia
no code implementations • ICLR 2018 • Jianfei Chen, Jun Zhu
Previous attempts on reducing the receptive field size by subsampling neighbors do not have any convergence guarantee, and their receptive field size per node is still in the order of hundreds.
no code implementations • 25 Jan 2018 • Haosheng Zou, Hang Su, Shihong Song, Jun Zhu
Crowd behavior understanding is crucial yet challenging across a wide range of applications, since crowd behavior is inherently determined by a sequential decision-making process based on various factors, such as the pedestrians' own destinations, interaction with nearby pedestrians and anticipation of upcoming events.
2 code implementations • ICML 2018 • Tianyu Pang, Chao Du, Jun Zhu
In this paper, we show that a properly designed classifier can improve robustness to adversarial attacks and lead to better prediction results.
1 code implementation • 7 Mar 2018 • Xingxing Wei, Jun Zhu, Hang Su
Although adversarial samples of deep neural networks (DNNs) have been intensively studied on static images, their extensions in videos are never explored.
no code implementations • 29 Mar 2018 • Zhize Li, Tianyi Zhang, Shuyu Cheng, Jun Zhu, Jian Li
In this paper, we apply the variance reduction tricks on Hamiltonian Monte Carlo and achieve better theoretical convergence results compared with the variance-reduced Langevin dynamics.
1 code implementation • 31 Mar 2018 • Alexey Kurakin, Ian Goodfellow, Samy Bengio, Yinpeng Dong, Fangzhou Liao, Ming Liang, Tianyu Pang, Jun Zhu, Xiaolin Hu, Cihang Xie, Jian-Yu Wang, Zhishuai Zhang, Zhou Ren, Alan Yuille, Sangxia Huang, Yao Zhao, Yuzhe Zhao, Zhonglin Han, Junjiajia Long, Yerkebulan Berdibekov, Takuya Akiba, Seiya Tokui, Motoki Abe
To accelerate research on adversarial examples and robustness of machine learning classifiers, Google Brain organized a NIPS 2017 competition that encouraged researchers to develop new methods to generate adversarial examples as well as to develop new ways to defend against them.
no code implementations • 10 Apr 2018 • Zihao Xiao, Jianfei Chen, Jun Zhu
We also propose an extension to train pLSI and a method to prune the network to obey the limited fan-in of some NMSs.
1 code implementation • NeurIPS 2018 • Chongxuan Li, Max Welling, Jun Zhu, Bo Zhang
We propose Graphical Generative Adversarial Networks (Graphical-GAN) to model structured data.
1 code implementation • CVPR 2018 • Juzheng Li, Hang Su, Jun Zhu, Siyu Wang, Bo Zhang
The machine thus performs as an instructor to extract the essay-level contradictions as the Guidance.
1 code implementation • ICML 2018 • Hanjun Dai, Hui Li, Tian Tian, Xin Huang, Lin Wang, Jun Zhu, Le Song
Deep learning on graph structures has shown exciting results in various applications.
3 code implementations • ICML 2018 • Jiaxin Shi, Shengyang Sun, Jun Zhu
Recently there have been increasing interests in learning and inference with implicit distributions (i. e., distributions without tractable densities).
1 code implementation • 4 Jul 2018 • Chang Liu, Jingwei Zhuo, Pengyu Cheng, Ruiyi Zhang, Jun Zhu, Lawrence Carin
Particle-based variational inference methods (ParVIs) have gained attention in the Bayesian inference literature, for their capacity to yield flexible and accurate approximations.
no code implementations • ICLR 2019 • Chao Du, Kun Xu, Chongxuan Li, Jun Zhu, Bo Zhang
Implicit generative models are difficult to train as no explicit density functions are defined.
no code implementations • 10 Jul 2018 • Kun Xu, Haoyu Liang, Jun Zhu, Hang Su, Bo Zhang
Deep generative models have shown promising results in generating realistic images, but it is still non-trivial to generate images with complicated structures.
no code implementations • 16 Sep 2018 • Yujie Wu, Lei Deng, Guoqi Li, Jun Zhu, Luping Shi
Spiking neural networks (SNNs) that enables energy efficient implementation on emerging neuromorphic hardware are gaining more attention.
no code implementations • 9 Oct 2018 • Mengchen Liu, Shixia Liu, Hang Su, Kelei Cao, Jun Zhu
Deep neural networks (DNNs) are vulnerable to maliciously generated adversarial examples.
no code implementations • 10 Oct 2018 • Yichi Zhou, Tongzheng Ren, Jialian Li, Dong Yan, Jun Zhu
In this paper, we present a novel technique, lazy update, which can avoid traversing the whole game tree in CFR, as well as a novel analysis on the regret of CFR with lazy update.
1 code implementation • NeurIPS 2018 • Yucen Luo, Tian Tian, Jiaxin Shi, Jun Zhu, Bo Zhang
We propose a new approach that includes a deep generative model (DGM) to characterize low-level features of the data, and a statistical relational model for noisy pairwise annotations on its subset.
no code implementations • 16 Nov 2018 • You Qiaoben, Zheng Wang, Jianguo Li, Yinpeng Dong, Yu-Gang Jiang, Jun Zhu
Binary neural networks have great resource and computing efficiency, while suffer from long training procedure and non-negligible accuracy drops, when comparing to the full-precision counterparts.
no code implementations • NeurIPS 2018 • Jianfei Chen, Jun Zhu, Yee Whye Teh, Tong Zhang
However, sEM has a slower asymptotic convergence rate than batch EM, and requires a decreasing sequence of step sizes, which is difficult to tune.
no code implementations • ICLR 2020 • Chongxuan Li, Chao Du, Kun Xu, Max Welling, Jun Zhu, Bo Zhang
We propose a black-box algorithm called {\it Adversarial Variational Inference and Learning} (AdVIL) to perform inference and learning on a general Markov random field (MRF).
6 code implementations • 25 Jan 2019 • Tianyu Pang, Kun Xu, Chao Du, Ning Chen, Jun Zhu
Though deep neural networks have achieved significant progress on various tasks, often enhanced by model ensemble, existing high-performance models can be vulnerable to adversarial attacks.
no code implementations • 25 Jan 2019 • Yinpeng Dong, Fan Bao, Hang Su, Jun Zhu
3) We propose to improve the consistency of neurons on adversarial example subset by an adversarial training algorithm with a consistent loss.
no code implementations • 27 Jan 2019 • Haosheng Zou, Tongzheng Ren, Dong Yan, Hang Su, Jun Zhu
Reward shaping is one of the most effective methods to tackle the crucial yet challenging problem of credit assignment in Reinforcement Learning (RL).
1 code implementation • 1 Feb 2019 • Chang Liu, Jingwei Zhuo, Jun Zhu
It is known that the Langevin dynamics used in MCMC is the gradient flow of the KL divergence on the Wasserstein space, which helps convergence analysis and inspires recent particle-based variational inference methods (ParVIs).
no code implementations • 25 Feb 2019 • Zhijie Deng, Yinpeng Dong, Jun Zhu
We present batch virtual adversarial training (BVAT), a novel regularization method for graph convolutional networks (GCNs).
1 code implementation • ICLR 2019 • Ziyu Wang, Tongzheng Ren, Jun Zhu, Bo Zhang
While Bayesian neural networks (BNNs) have drawn increasing attention, their posterior inference remains challenging, due to the high-dimensional and over-parameterized nature.
1 code implementation • ICCV 2019 • Zhijie Deng, Yucen Luo, Jun Zhu
Deep learning methods have shown promise in unsupervised domain adaptation, which aims to leverage a labeled source domain to learn a classifier for the unlabeled target domain with a different distribution.
Ranked #3 on Domain Adaptation on SVNH-to-MNIST
2 code implementations • CVPR 2019 • Yinpeng Dong, Tianyu Pang, Hang Su, Jun Zhu
In this paper, we propose a translation-invariant attack method to generate more transferable adversarial examples against the defense models.
no code implementations • CVPR 2019 • Yinpeng Dong, Hang Su, Baoyuan Wu, Zhifeng Li, Wei Liu, Tong Zhang, Jun Zhu
In this paper, we evaluate the robustness of state-of-the-art face recognition models in the decision-based black-box attack setting, where the attackers have no access to the model parameters and gradients, but can only acquire hard-label predictions by sending queries to the target model.
no code implementations • ICLR 2019 • Yichi Zhou, Jun Zhu
We provide insights into the relationship between $A^*$ sampling and probability matching by analyzing a nontrivial special case in which the state space is partitioned into two subsets.
no code implementations • ICLR 2019 • Jialian Li, Hang Su, Jun Zhu
We can solve these tasks by first building models for other agents and then finding the optimal policy with these models.
1 code implementation • 11 May 2019 • Fan Bao, Hang Su, Jun Zhu
Besides, our framework can be extended to semi-supervised boosting, where the boosted model learns a joint distribution of data and labels.
no code implementations • 23 May 2019 • Tsung Wei Tsai, Chongxuan Li, Jun Zhu
We consider the learning from noisy labels (NL) problem which emerges in many real-world applications.
2 code implementations • ICLR 2020 • Tianyu Pang, Kun Xu, Yinpeng Dong, Chao Du, Ning Chen, Jun Zhu
Previous work shows that adversarially robust generalization requires larger sample complexity, and the same dataset, e. g., CIFAR-10, which enables good standard accuracy may not suffice to train robust models.
2 code implementations • 27 May 2019 • Jiaxin Shi, Mohammad Emtiyaz Khan, Jun Zhu
Inference in Gaussian process (GP) models is computationally challenging for large data, and often difficult to approximate with a small number of inducing points.
1 code implementation • NeurIPS 2019 • Kun Xu, Chongxuan Li, Jun Zhu, Bo Zhang
Deep generative models (DGMs) have shown promise in image generation.
2 code implementations • NeurIPS 2019 • Shuyu Cheng, Yinpeng Dong, Tianyu Pang, Hang Su, Jun Zhu
We consider the black-box adversarial setting, where the adversary has to generate adversarial perturbations without access to the target models to compute gradients.
no code implementations • 15 Sep 2019 • Zheyu Yang, Yujie Wu, Guanrui Wang, Yukuan Yang, Guoqi Li, Lei Deng, Jun Zhu, Luping Shi
To the best of our knowledge, DashNet is the first framework that can integrate and process ANNs and SNNs in a hybrid paradigm, which provides a novel solution to achieve both effectiveness and efficiency for high-speed object tracking.
no code implementations • 18 Sep 2019 • Zheng Zhang, Ruiqing Yin, Jun Zhu, Pierre Zweigenbaum
Recent work in cross-lingual contextual word embedding learning cannot handle multi-sense words well.
no code implementations • 20 Sep 2019 • Yucen Luo, Jun Zhu, Tomas Pfister
Recently deep neural networks have shown their capacity to memorize training data, even with noisy labels, which hurts generalization performance.
1 code implementation • ICLR 2020 • Tianyu Pang, Kun Xu, Jun Zhu
Our experiments on CIFAR-10 and CIFAR-100 demonstrate that MI can further improve the adversarial robustness for the models trained by mixup and its variants.
no code implementations • 25 Sep 2019 • Haoyu Liang, Zhihao Ouyang, Hang Su, Yuyuan Zeng, Zihao He, Shu-Tao Xia, Jun Zhu, Bo Zhang
Convolutional neural networks (CNNs) have often been treated as “black-box” and successfully used in a range of tasks.
1 code implementation • 25 Sep 2019 • Zhijie Deng, Yucen Luo, Jun Zhu, Bo Zhang
Bayesian neural networks (BNNs) introduce uncertainty estimation to deep networks by performing Bayesian inference on network weights.
1 code implementation • 29 Sep 2019 • Kun Xu, Chongxuan Li, Jun Zhu, Bo Zhang
There are existing efforts that model the training dynamics of GANs in the parameter space but the analysis cannot directly motivate practically effective stabilizing methods.
Ranked #37 on Image Generation on CIFAR-10 (Inception score metric)
no code implementations • NeurIPS 2019 • Justin Cosentino, Jun Zhu
We propose Generative Well-intentioned Networks (GWINs), a novel framework for increasing the accuracy of certainty-based, closed-world classifiers.
1 code implementation • 22 Nov 2019 • Zhijie Deng, Yucen Luo, Jun Zhu, Bo Zhang
Bayesian neural networks (BNNs) augment deep networks with uncertainty quantification by Bayesian treatment of the network weights.
no code implementations • ECCV 2020 • Xiao Yang, Fangyun Wei, Hongyang Zhang, Jun Zhu
We consider universal adversarial patches for faces -- small visual elements whose addition to a face image reliably destroys the performance of face detectors.
1 code implementation • 5 Dec 2019 • Justin Cosentino, Federico Zaiter, Dan Pei, Jun Zhu
Recent work on deep neural network pruning has shown there exist sparse subnetworks that achieve equal or improved accuracy, training time, and loss using fewer network parameters when compared to their dense counterparts.
1 code implementation • 20 Dec 2019 • Chongxuan Li, Kun Xu, Jiashuo Liu, Jun Zhu, Bo Zhang
It is formulated as a three-player minimax game consisting of a generator, a classifier and a discriminator, and therefore is referred to as Triple Generative Adversarial Network (Triple-GAN).
no code implementations • 26 Dec 2019 • Yinpeng Dong, Qi-An Fu, Xiao Yang, Tianyu Pang, Hang Su, Zihao Xiao, Jun Zhu
Deep neural networks are vulnerable to adversarial examples, which becomes one of the most important research problems in the development of deep learning.
no code implementations • ICLR 2020 • Shiyu Huang, Hang Su, Jun Zhu, Ting Chen
Partially Observable Markov Decision Processes (POMDPs) are popular and flexible models for real-world decision-making applications that demand the information from past observations to make optimal decisions.
no code implementations • ICLR 2020 • Zhaocheng Liu, Qiang Liu, Haoli Zhang, Jun Zhu
In recent years, substantial progress has been made on graph convolutional networks (GCN).
no code implementations • 26 Jan 2020 • Kelei Cao, Mengchen Liu, Hang Su, Jing Wu, Jun Zhu, Shixia Liu
The key is to compare and analyze the datapaths of both the adversarial and normal examples.
1 code implementation • NeurIPS 2020 • Yinpeng Dong, Zhijie Deng, Tianyu Pang, Hang Su, Jun Zhu
Adversarial training (AT) is among the most effective techniques to improve model robustness by augmenting training data with adversarial examples.
1 code implementation • pproximateinference AABI Symposium 2019 • Ziyu Wang, Shuyu Cheng, Yueru Li, Jun Zhu, Bo Zhang
Score matching provides an effective approach to learning flexible unnormalized models, but its scalability is limited by the need to evaluate a second-order derivative.
1 code implementation • NeurIPS 2020 • Tianyu Pang, Xiao Yang, Yinpeng Dong, Kun Xu, Jun Zhu, Hang Su
Adversarial training (AT) is one of the most effective defenses against adversarial attacks for deep learning models.
1 code implementation • ICML 2020 • Jianfei Chen, Cheng Lu, Biqi Chenli, Jun Zhu, Tian Tian
Generative flows are promising tractable models for density modeling that define probabilistic distributions with invertible transformations.
Ranked #30 on Image Generation on CIFAR-10 (bits/dimension metric)
1 code implementation • 6 Mar 2020 • Liyuan Wang, Bo Lei, Qian Li, Hang Su, Jun Zhu, Yi Zhong
Continual acquisition of novel experience without interfering previously learned knowledge, i. e. continual learning, is critical for artificial neural networks, but limited by catastrophic forgetting.
1 code implementation • ICCV 2021 • Xiao Yang, Yinpeng Dong, Tianyu Pang, Hang Su, Jun Zhu, Yuefeng Chen, Hui Xue
As billions of personal data being shared through social media and network, the data privacy and security have drawn an increasing attention.
no code implementations • ICLR 2020 • Yucen Luo, Alex Beatson, Mohammad Norouzi, Jun Zhu, David Duvenaud, Ryan P. Adams, Ricky T. Q. Chen
Standard variational lower bounds used to train latent variable models produce biased estimates of most quantities of interest.
no code implementations • ICLR 2020 • Yichi Zhou, Jialian Li, Jun Zhu
Posterior sampling for reinforcement learning (PSRL) is a useful framework for making decisions in an unknown environment.
no code implementations • ICLR 2020 • Yichi Zhou, Tongzheng Ren, Jialian Li, Dong Yan, Jun Zhu
In this paper, we present Lazy-CFR, a CFR algorithm that adopts a lazy update strategy to avoid traversing the whole game tree in each round.
1 code implementation • ICML 2020 • Yuhao Zhou, Jiaxin Shi, Jun Zhu
Estimating the score, i. e., the gradient of log density function, from a set of samples generated by an unknown distribution is a fundamental task in inference and learning of probabilistic models that involve flexible yet intractable densities.
no code implementations • 5 Jun 2020 • Yujie Wu, Rong Zhao, Jun Zhu, Feng Chen, Mingkun Xu, Guoqi Li, Sen Song, Lei Deng, Guanrui Wang, Hao Zheng, Jing Pei, Youhui Zhang, Mingguo Zhao, Luping Shi
We demonstrate the advantages of this model in multiple different tasks, including few-shot learning, continual learning, and fault-tolerance learning in neuromorphic vision sensors.
no code implementations • 14 Jun 2020 • Zhiheng Zhang, Wen-Bo Hu, Tian Tian, Jun Zhu
In this paper, we present the dynamic window-level Granger causality method (DWGC) for multi-channel time series data.
no code implementations • NeurIPS 2020 • Peng Cui, Wen-Bo Hu, Jun Zhu
Accurate quantification of uncertainty is crucial for real-world applications of machine learning.
no code implementations • ICLR 2021 • Feng Zhou, Yixuan Zhang, Jun Zhu
Hawkes process provides an effective statistical framework for analyzing the time-dependent interaction of neuronal spiking activities.
1 code implementation • NeurIPS 2020 • Tianyu Pang, Kun Xu, Chongxuan Li, Yang song, Stefano Ermon, Jun Zhu
Several machine learning applications involve the optimization of higher-order derivatives (e. g., gradients of gradients) during training, which can be expensive in respect to memory and computation even with automatic differentiation.
2 code implementations • 8 Jul 2020 • Xiao Yang, Dingcheng Yang, Yinpeng Dong, Hang Su, Wenjian Yu, Jun Zhu
Based on large-scale evaluations, the commercial FR API services fail to exhibit acceptable performance on robustness evaluation, and we also draw several important conclusions for understanding the adversarial robustness of FR models and providing insights for the design of robust FR models.
1 code implementation • ECCV 2020 • Haoyu Liang, Zhihao Ouyang, Yuyuan Zeng, Hang Su, Zihao He, Shu-Tao Xia, Jun Zhu, Bo Zhang
Most existing works attempt post-hoc interpretation on a pre-trained model, while neglecting to reduce the entanglement underlying the model.
no code implementations • 15 Sep 2020 • Chen Ma, Shuyu Cheng, Li Chen, Jun Zhu, Junhai Yong
In each iteration, SWITCH first tries to update the current sample along the direction of $\hat{\mathbf{g}}$, but considers switching to its opposite direction $-\hat{\mathbf{g}}$ if our algorithm detects that it does not increase the value of the attack objective function.
no code implementations • 28 Sep 2020 • Zhijie Deng, Xiao Yang, Hao Zhang, Yinpeng Dong, Jun Zhu
Despite their theoretical appealingness, Bayesian neural networks (BNNs) are falling far behind in terms of adoption in real-world applications compared with normal NNs, mainly due to their limited scalability in training, and low fidelity in their uncertainty estimates.
2 code implementations • ICLR 2021 • Tianyu Pang, Xiao Yang, Yinpeng Dong, Hang Su, Jun Zhu
Adversarial training (AT) is one of the most effective strategies for promoting model robustness.
1 code implementation • 5 Oct 2020 • Zhijie Deng, Jun Zhu
Despite their theoretical appealingness, Bayesian neural networks (BNNs) are left behind in real-world adoption, mainly due to persistent concerns on their scalability, accessibility, and reliability.
1 code implementation • NeurIPS 2020 • Fan Bao, Chongxuan Li, Kun Xu, Hang Su, Jun Zhu, Bo Zhang
This paper presents a bi-level score matching (BiSM) method to learn EBLVMs with general structures by reformulating SM as a bi-level optimization problem.
1 code implementation • NeurIPS Workshop ICBINB 2020 • Fan Bao, Kun Xu, Chongxuan Li, Lanqing Hong, Jun Zhu, Bo Zhang
The learning and evaluation of energy-based latent variable models (EBLVMs) without any structural assumptions are highly challenging, because the true posteriors and the partition functions in such models are generally intractable.
1 code implementation • NeurIPS 2020 • Ziyu Wang, Bin Dai, David Wipf, Jun Zhu
The recent, counter-intuitive discovery that deep generative models (DGMs) can frequently assign a higher likelihood to outliers has implications for both outlier detection applications as well as our overall understanding of generative modeling.
1 code implementation • NeurIPS 2020 • Guoqiang Wu, Jun Zhu
On the other hand, when directly optimizing SA with its surrogate loss, it has learning guarantees that depend on $O(\sqrt{c})$ for both HL and SA measures.
1 code implementation • NeurIPS 2020 • Zhijie Deng, Yinpeng Dong, Shifeng Zhang, Jun Zhu
In this work, we decouple the training of a network with stochastic architectures (NSA) from NAS and provide a first systematical investigation on it as a stand-alone problem.
1 code implementation • 14 Dec 2020 • Qipeng Guo, Zhijing Jin, Ziyu Wang, Xipeng Qiu, Weinan Zhang, Jun Zhu, Zheng Zhang, David Wipf
Cycle-consistent training is widely used for jointly learning a forward and inverse mapping between two domains of interest without the cumbersome requirement of collecting matched pairs within each domain.
no code implementations • 16 Dec 2020 • Qingyi Pan, WenBo Hu, Jun Zhu
Though deep learning methods have recently been developed to give superior forecasting results, it is crucial to improve the interpretability of time series models.
no code implementations • 1 Jan 2021 • Guan Wang, Dong Yan, Hang Su, Jun Zhu
In this work, we point out that the optimal value of n actually differs on each data point, while the fixed value n is a rough average of them.
no code implementations • 1 Jan 2021 • Shiyu Huang, Bin Wang, Dong Li, Jianye Hao, Jun Zhu, Ting Chen
In our method, we introduce a new set of variables called cost maps, which can help the A* router to find out proper paths to achieve the global object.
no code implementations • CVPR 2021 • Liyuan Wang, Kuo Yang, Chongxuan Li, Lanqing Hong, Zhenguo Li, Jun Zhu
Continual learning usually assumes the incoming data are fully labeled, which might not be applicable in real applications.
no code implementations • 5 Jan 2021 • Qijun Luo, Zhili Liu, Lanqing Hong, Chongxuan Li, Kuo Yang, Liyuan Wang, Fengwei Zhou, Guilin Li, Zhenguo Li, Jun Zhu
Semi-supervised domain adaptation (SSDA), which aims to learn models in a partially labeled target domain with the assistance of the fully labeled source domain, attracts increasing attention in recent years.
no code implementations • 11 Jan 2021 • Yuanyuan Ding, Junchi Yan, Guoqiang Hu, Jun Zhu
This paper discloses a novel visual inspection system for liquid crystal display (LCD), which is currently a dominant type in the FPD industry.
no code implementations • 25 Jan 2021 • Jun Zhu, Ye Chen, Frank Brinker, Winfried Decking, Sergey Tomin, Holger Schlarb
We also show the scalability and interpretability of the model by sharing the same decoder with more than one encoder used for different setups of the photoinjector, and propose a pragmatic way to model a facility with various diagnostics and working points.
1 code implementation • 23 Feb 2021 • Xiao Li, Jianmin Li, Ting Dai, Jie Shi, Jun Zhu, Xiaolin Hu
A detection model based on the classification model EfficientNet-B7 achieved a top-1 accuracy of 53. 95%, surpassing previous state-of-the-art classification models trained on ImageNet, suggesting that accurate localization information can significantly boost the performance of classification models on ImageNet-A.
no code implementations • 24 Feb 2021 • Qiang Liu, Zhaocheng Liu, Haoli Zhang, Yuntian Chen, Jun Zhu
Accordingly, we can design an automatic feature crossing method to find feature interactions in DNN, and use them as cross features in LR.
1 code implementation • ICLR 2021 • Cheng Lu, Jianfei Chen, Chongxuan Li, Qiuhao Wang, Jun Zhu
Through theoretical analysis, we show that the function space of ImpFlow is strictly richer than that of ResFlows.
no code implementations • ICCV 2021 • Yinpeng Dong, Xiao Yang, Zhijie Deng, Tianyu Pang, Zihao Xiao, Hang Su, Jun Zhu
Although deep neural networks (DNNs) have made rapid progress in recent years, they are vulnerable in adversarial environments.
1 code implementation • CVPR 2021 • Zhijie Deng, Xiao Yang, Shizhen Xu, Hang Su, Jun Zhu
Despite their appealing flexibility, deep neural networks (DNNs) are vulnerable against adversarial examples.
no code implementations • 28 Mar 2021 • Peng Cui, Zhijie Deng, WenBo Hu, Jun Zhu
It is critical yet challenging for deep learning models to properly characterize uncertainty that is pervasive in real-world environments.
2 code implementations • 9 Apr 2021 • Tim Pearce, Jun Zhu
This paper describes an AI agent that plays the popular first-person-shooter (FPS) video game `Counter-Strike; Global Offensive' (CSGO) from pixel input.
no code implementations • 19 Apr 2021 • Liyuan Wang, Qian Li, Yi Zhong, Jun Zhu
Our solution is based on the observation that continual learning of a task sequence inevitably interferes few-shot generalization, which makes it highly nontrivial to extend few-shot learning strategies to continual learning scenarios.
1 code implementation • ICLR 2021 • Tsung Wei Tsai, Chongxuan Li, Jun Zhu
We present Mixture of Contrastive Experts (MiCE), a unified probabilistic clustering framework that simultaneously exploits the discriminative representations learned by contrastive learning and the semantic structures captured by a latent mixture model.
Ranked #9 on Image Clustering on Imagenet-dog-15
no code implementations • 9 May 2021 • Qi-An Fu, Yinpeng Dong, Hang Su, Jun Zhu
Deep learning models are vulnerable to adversarial examples, which can fool a target classifier by imposing imperceptible perturbations onto natural examples.
no code implementations • NeurIPS 2021 • Guoqiang Wu, Chongxuan Li, Kun Xu, Jun Zhu
Our results show that learning algorithms with the consistent univariate loss have an error bound of $O(c)$ ($c$ is the number of labels), while algorithms with the inconsistent pairwise loss depend on $O(\sqrt{c})$ as shown in prior work.
no code implementations • NeurIPS 2021 • Ziyu Wang, Yuhao Zhou, Tongzheng Ren, Jun Zhu
Recent years have witnessed an upsurge of interest in employing flexible machine learning models for instrumental variable (IV) regression, but the development of uncertainty quantification methodology is still lacking.
no code implementations • CVPR 2021 • Shilong Liu, Lei Zhang, Xiao Yang, Hang Su, Jun Zhu
We study the problem of unsupervised discovery and segmentation of object parts, which, as an intermediate local representation, are capable of finding intrinsic object structure and providing more explainable recognition results.
1 code implementation • CVPR 2022 • Tianyu Pang, Huishuai Zhang, Di He, Yinpeng Dong, Hang Su, Wei Chen, Jun Zhu, Tie-Yan Liu
Along with this routine, we find that confidence and a rectified confidence (R-Con) can form two coupled rejection metrics, which could provably distinguish wrongly classified inputs from correctly classified ones.
no code implementations • 2 Jun 2021 • Yingtao Luo, Qiang Liu, Yuntian Chen, WenBo Hu, Tian Tian, Jun Zhu
Especially, the discovery of PDEs with highly nonlinear coefficients from low-quality data remains largely under-addressed.
1 code implementation • ICLR 2022 • Yinpeng Dong, Ke Xu, Xiao Yang, Tianyu Pang, Zhijie Deng, Hang Su, Jun Zhu
In this paper, we explore the memorization effect in adversarial training (AT) for promoting a deeper understanding of model capacity, convergence, generalization, and especially robust overfitting of the adversarially trained models.
1 code implementation • NeurIPS 2021 • Fan Bao, Guoqiang Wu, Chongxuan Li, Jun Zhu, Bo Zhang
Our results can explain some mysterious behaviours of the bilevel programming in practice, for instance, overfitting to the validation set.
no code implementations • 9 Jun 2021 • Tim Pearce, Alexandra Brintrup, Jun Zhu
It is often remarked that neural networks fail to increase their uncertainty when predicting on data far from the training distribution.
no code implementations • 9 Jun 2021 • Feng Zhou, Quyu Kong, Yixuan Zhang, Cheng Feng, Jun Zhu
Hawkes processes are a class of point processes that have the ability to model the self- and mutual-exciting phenomena.
no code implementations • 14 Jun 2021 • Xu Han, Zhengyan Zhang, Ning Ding, Yuxian Gu, Xiao Liu, Yuqi Huo, Jiezhong Qiu, Yuan YAO, Ao Zhang, Liang Zhang, Wentao Han, Minlie Huang, Qin Jin, Yanyan Lan, Yang Liu, Zhiyuan Liu, Zhiwu Lu, Xipeng Qiu, Ruihua Song, Jie Tang, Ji-Rong Wen, Jinhui Yuan, Wayne Xin Zhao, Jun Zhu
Large-scale pre-trained models (PTMs) such as BERT and GPT have recently achieved great success and become a milestone in the field of artificial intelligence (AI).
1 code implementation • NeurIPS 2021 • Ziyu Wang, Yuhao Zhou, Tongzheng Ren, Jun Zhu
Recent years have witnessed an upsurge of interest in employing flexible machine learning models for instrumental variable (IV) regression, but the development of uncertainty quantification methodology is still lacking.
no code implementations • ICML Workshop AML 2021 • You Qiaoben, Xinning Zhou, Chengyang Ying, Jun Zhu
Deep reinforcement learning (DRL) policies are vulnerable to the adversarial attack on their observations, which may mislead real-world RL agents to catastrophic failures.
1 code implementation • NeurIPS 2021 • Tianyu Pang, Xiao Yang, Yinpeng Dong, Hang Su, Jun Zhu
Collecting training data from untrusted sources exposes machine learning services to poisoning adversaries, who maliciously manipulate training data to degrade the model accuracy.
no code implementations • ICML Workshop AML 2021 • Chengyang Ying, Xinning Zhou, Dong Yan, Jun Zhu
Though deep reinforcement learning (DRL) has obtained substantial success, it may encounter catastrophic failures due to the intrinsic uncertainty caused by stochastic policies and environment variability.
no code implementations • CVPR 2021 • Zhenwei Miao, Jikai Chen, Hongyu Pan, Ruiwen Zhang, Kaixuan Liu, Peihan Hao, Jun Zhu, Yang Wang, Xin Zhan
Quantization-based methods are widely used in LiDAR points 3D object detection for its efficiency in extracting context information.
no code implementations • 29 Jun 2021 • Yichi Zhou, Shihong Song, Huishuai Zhang, Jun Zhu, Wei Chen, Tie-Yan Liu
However, it is in general unknown how to deriveefficient and effective EE trade-off methods for non-linearcomplex tasks, suchas contextual bandit with deep neural network as the reward function.
no code implementations • CVPR 2021 • Zihao Xiao, Xianfeng Gao, Chilin Fu, Yinpeng Dong, Wei Gao, Xiaolu Zhang, Jun Zhou, Jun Zhu
However, deep CNNs are vulnerable to adversarial patches, which are physically realizable and stealthy, raising new security concerns on the real-world applications of these models.
no code implementations • 30 Jun 2021 • You Qiaoben, Chengyang Ying, Xinning Zhou, Hang Su, Jun Zhu, Bo Zhang
In this paper, we provide a framework to better understand the existing methods by reformulating the problem of adversarial attacks on reinforcement learning in the function space.
1 code implementation • ICML Workshop AML 2021 • Xiao Yang, Yinpeng Dong, Tianyu Pang, Hang Su, Jun Zhu
Transfer-based adversarial attacks can evaluate model robustness in the black-box setting.
1 code implementation • NeurIPS 2021 • Shuyu Cheng, Guoqiang Wu, Jun Zhu
Finally, our theoretical results are confirmed by experiments on several numerical benchmarks as well as adversarial attacks.