
Learning Manifold Implicitly via Explicit HeatKernel Learning
Manifold learning is a fundamental problem in machine learning with nume...
read it

Repulsive Attention: Rethinking Multihead Attention as Bayesian Inference
The neural attention mechanism plays an important role in many natural l...
read it

StructureAware HumanAction Generation
Generating longrange skeletonbased human actions has been a challengin...
read it

Generative Semantic Hashing Enhanced via Boltzmann Machines
Generative semantic hashing is a promising technique for largescale inf...
read it

Graph Neural Networks with Composite Kernels
Learning on graph structured data has drawn increasing interest in recen...
read it

Towards Understanding the Adversarial Vulnerability of Skeletonbased Action Recognition
Skeletonbased action recognition has attracted increasing attention due...
read it

Reward Constrained Interactive Recommendation with Natural Language Feedback
Textbased interactive recommendation provides richer user feedback and ...
read it

Improving Adversarial Text Generation by Modeling the Distant Future
Autoregressive text generation models usually focus on local fluency, a...
read it

Towards Faithful Neural TabletoText Generation with ContentMatching Constraints
Text generation from a knowledge base aims to translate knowledge triple...
read it

Discretized Bottleneck in VAE: PosteriorCollapseFree SequencetoSequence Learning
Variational autoencoders (VAEs) are important tools in endtoend repres...
read it

Decomposed Adversarial Learned Inference
Effective inference for a generative adversarial model remains an import...
read it

Feature Quantization Improves GAN Training
The instability in GAN training has been a longstanding problem despite...
read it

NestedWasserstein SelfImitation Learning for Sequence Generation
Reinforcement learning (RL) has been widely studied for improving sequen...
read it

Learning Diverse Stochastic HumanAction Generators by Learning Smooth Latent Transitions
Humanmotion generation is a longstanding challenging task due to the r...
read it

KernelNet: A DataDependent Kernel Parameterization for Deep Generative Modeling
Learning with kernels is an often resorted tool in modern machine learni...
read it

Finegrained Attention and Featuresharing Generative Adversarial Networks for Single Image SuperResolution
The traditional superresolution methods that aim to minimize the mean s...
read it

Implicit Deep Latent Variable Models for Text Generation
Deep latent variable models (LVM) such as variational autoencoder (VAE)...
read it

Document Hashing with MixturePrior Generative Models
Hashing is promising for largescale information retrieval tasks thanks ...
read it

Bayesian Uncertainty Matching for Unsupervised Domain Adaptation
Domain adaptation is an important technique to alleviate performance deg...
read it

On NormAgnostic Robustness of Adversarial Training
Adversarial examples are carefully perturbed inputs for fooling machine...
read it

TopicGuided Variational Autoencoders for Text Generation
We propose a topicguided variational autoencoder (TGVAE) model for text...
read it

Scalable Thompson Sampling via Optimal Transport
Thompson sampling (TS) is a class of algorithms for sequential decision...
read it

Cyclical Stochastic Gradient MCMC for Bayesian Deep Learning
The posteriors over neural network weights are high dimensional and mult...
read it

Improving SequencetoSequence Learning via Optimal Transport
Sequencetosequence models are commonly trained via maximum likelihood ...
read it

Adversarial Learning of a Sampler Based on an Unnormalized Distribution
We investigate adversarial learning in the case when only an unnormalize...
read it

Learning Saliency Maps for Adversarial PointCloud Generation
3D pointcloud recognition with deep neural network (DNN) has received r...
read it

SelfAdversarially Learned Bayesian Sampling
Scalable Bayesian sampling is playing an important role in modern machin...
read it

Variance Reduction in Stochastic ParticleOptimization Sampling
Stochastic particleoptimization sampling (SPOS) is a recentlydeveloped...
read it

Sequence Generation with Guider Network
Sequence generation with reinforcement learning (RL) has received signif...
read it

Is PGDAdversarial Training Necessary? Alternative Training via a SoftQuantization Network with NoisyNatural Samples Only
Recent work on adversarial attack and defense suggests that PGD is a uni...
read it

SecondOrder Adversarial Attack and Certifiable Robustness
We propose a powerful secondorder attack method that outperforms existi...
read it

Stochastic ParticleOptimization Sampling and the NonAsymptotic Convergence Theory
Particleoptimization sampling (POS) is a recently developed technique t...
read it

Distributionally Adversarial Attack
Recent work on adversarial attack has shown that Projected Gradient Desc...
read it

Policy Optimization as Wasserstein Gradient Flows
Policy optimization is a core component of reinforcement learning (RL), ...
read it

A Unified ParticleOptimization Framework for Scalable Bayesian Sampling
There has been recent interest in developing scalable Bayesian sampling ...
read it

Learning Structural Weight Uncertainty for Sequential DecisionMaking
Learning probability distributions on the weights of neural networks (NN...
read it

On Connecting Stochastic Gradient MCMC and Differential Privacy
Significant success has been realized recently on applying machine learn...
read it

Particle Optimization in Stochastic Gradient MCMC
Stochastic gradient Markov chain Monte Carlo (SGMCMC) has been increasi...
read it

ZeroShot Learning via ClassConditioned Deep Generative Models
We present a deep generative model for learning to predict classes not s...
read it

ALICE: Towards Understanding Adversarial Learning for Joint Distribution Matching
We investigate the nonidentifiability issues associated with bidirectio...
read it

A Convergence Analysis for A Class of Practical VarianceReduction Stochastic Gradient MCMC
Stochastic gradient Markov Chain Monte Carlo (SGMCMC) has been develope...
read it

ContinuousTime Flows for Deep Generative Models
Normalizing flows have been developed recently as a method for drawing s...
read it

Stochastic Gradient Monomial Gamma Sampler
Recent advances in stochastic gradient techniques have made it possible ...
read it

Scalable Bayesian Learning of Recurrent Neural Networks for Language Modeling
Recurrent neural networks (RNNs) have shown promising performance for la...
read it

On the Convergence of Stochastic Gradient MCMC Algorithms with HighOrder Integrators
Recent advances in Bayesian learning with largescale data have witnesse...
read it

Stochastic Gradient MCMC with Stale Gradients
Stochastic gradient MCMC (SGMCMC) has played an important role in large...
read it

Nonparametric Bayesian Topic Modelling with the Hierarchical PitmanYor Processes
The Dirichlet process and its extension, the PitmanYor process, are sto...
read it

Nonlinear Statistical Learning with Truncated Gaussian Graphical Models
We introduce the truncated Gaussian graphical model (TGGM) as a novel fr...
read it

Towards Unifying Hamiltonian Monte Carlo and Slice Sampling
We unify slice sampling and Hamiltonian Monte Carlo (HMC) sampling, demo...
read it

Bridging the Gap between Stochastic Gradient MCMC and Stochastic Optimization
Stochastic gradient Markov chain Monte Carlo (SGMCMC) methods are Bayes...
read it
Changyou Chen
is this you? claim profile
Assistant Professor in the Department of Computer Science and Engineering at the University at Buffalo, State University of New York