Preconditioned Stochastic Gradient Langevin Dynamics for Deep Neural Networks

23 December 2015

Chunyuan Li

Changyou Chen

David Carlson

Lawrence Carin

ODL

BDL

ArXiv (abs)PDF HTML

Papers citing "Preconditioned Stochastic Gradient Langevin Dynamics for Deep Neural Networks"

39 / 189 papers shown

Title
Variance Reduction in Stochastic Particle-Optimization SamplingInternational Conference on Machine Learning (ICML), 2018 Jianyi Zhang Yang Zhao Changyou Chen OT 157 13 0 20 Nov 2018
Projected BNNs: Avoiding weight-space pathologies by learning latent representations of neural network weights Melanie F. Pradier Weiwei Pan Jiayu Yao S. Ghosh Finale Doshi-velez UQCV BDL 189 10 0 16 Nov 2018
Langevin-gradient parallel tempering for Bayesian neural learning Rohitash Chandra Konark Jain R. Deo Sally Cripps BDL 116 47 0 11 Nov 2018
Deep Poisson gamma dynamical systems D. Guo Bo Chen Hao Zhang Mingyuan Zhou 146 29 0 26 Oct 2018
Finding Mixed Nash Equilibria of Generative Adversarial Networks Ya-Ping Hsieh Chen Liu S. Chakrabartty GAN 300 101 0 23 Oct 2018
Stochastic Gradient MCMC for State Space Models Christopher Aicher Yian Ma N. Foti E. Fox 197 23 0 22 Oct 2018
Adv-BNN: Improved Adversarial Defense through Robust Bayesian Neural Network Xuanqing Liu Yao Li Chongruo Wu Cho-Jui Hsieh AAML OOD 242 181 0 01 Oct 2018
Stochastic Particle-Optimization Sampling and the Non-Asymptotic Convergence Theory Jianyi Zhang Ruiyi Zhang Lawrence Carin Changyou Chen 323 47 0 05 Sep 2018
Nonparametric Gaussian Mixture Models for the Multi-Armed Bandit Iñigo Urteaga C. Wiggins 234 3 0 08 Aug 2018
Stochastic natural gradient descent draws posterior samples in function space Samuel L. Smith Daniel Duckworth Semon Rezchikov Quoc V. Le Jascha Narain Sohl-Dickstein BDL 227 7 0 25 Jun 2018
Structured Variational Learning of Bayesian Neural Networks with Horseshoe Priors S. Ghosh Jiayu Yao Finale Doshi-Velez BDL UQCV 171 81 0 13 Jun 2018
Fast and Scalable Bayesian Deep Learning by Weight-Perturbation in Adam Mohammad Emtiyaz Khan Didrik Nielsen Voot Tangkaratt Wu Lin Y. Gal Akash Srivastava ODL 347 281 0 13 Jun 2018
Meta-Learning for Stochastic Gradient MCMC Wenbo Gong Yingzhen Li José Miguel Hernández-Lobato BDL 307 44 0 12 Jun 2018
Scalable Natural Gradient Langevin Dynamics in Practice Henri Palacci H. Hess BDL 119 8 0 07 Jun 2018
A Unified Particle-Optimization Framework for Scalable Bayesian Sampling Changyou Chen Ruiyi Zhang Wenlin Wang Bai Li Liqun Chen 235 91 0 29 May 2018
Learning Sparse Structured Ensembles with SG-MCMC and Network Pruning Yichi Zhang Zhijian Ou 180 0 0 01 Mar 2018
Deep Bayesian Bandits Showdown: An Empirical Comparison of Bayesian Deep Networks for Thompson SamplingInternational Conference on Learning Representations (ICLR), 2018 C. Riquelme George Tucker Jasper Snoek BDL 237 376 0 26 Feb 2018
Learning Structural Weight Uncertainty for Sequential Decision-Making Ruiyi Zhang Chunyuan Li Changyou Chen Lawrence Carin BDL UQCV 326 26 0 30 Dec 2017
On Connecting Stochastic Gradient MCMC and Differential PrivacyInternational Conference on Artificial Intelligence and Statistics (AISTATS), 2017 Bai Li Changyou Chen Hao Liu Lawrence Carin 168 40 0 25 Dec 2017
Natural Langevin Dynamics for Neural Networks Gaétan Marceau-Caron Yann Ollivier BDL 151 30 0 04 Dec 2017
Riemannian Stein Variational Gradient Descent for Bayesian Inference Chang-rui Liu Jun Zhu 124 69 0 30 Nov 2017
A Convergence Analysis for A Class of Practical Variance-Reduction Stochastic Gradient MCMC Changyou Chen Wenlin Wang Yizhe Zhang Qinliang Su Lawrence Carin 187 28 0 04 Sep 2017
Continuous-Time Flows for Efficient Inference and Density Estimation Changyou Chen Chunyuan Li Liquan Chen Wenlin Wang Yunchen Pu Lawrence Carin TPM 266 59 0 04 Sep 2017
Differentially Private Regression for Discrete-Time Survival Analysis T. Nguyen S. Hui 116 12 0 24 Aug 2017
A Divergence Bound for Hybrids of MCMC and Variational Inference and an Application to Langevin Dynamics and SGVI Justin Domke BDL 143 6 0 20 Jun 2017
Fractional Langevin Monte Carlo: Exploring Lévy Driven Stochastic Differential Equations for Markov Chain Monte CarloInternational Conference on Machine Learning (ICML), 2017 Umut Simsekli 146 46 0 12 Jun 2017
Deep Latent Dirichlet Allocation with Topic-Layer-Adaptive Stochastic Gradient Riemannian MCMCInternational Conference on Machine Learning (ICML), 2017 Yulai Cong Bo Chen Hongwei Liu Mingyuan Zhou BDL 172 68 0 06 Jun 2017
Bayesian Recurrent Neural Networks Meire Fortunato Charles Blundell Oriol Vinyals BDL 353 200 0 10 Apr 2017
Scalable Bayesian Learning of Recurrent Neural Networks for Language Modeling Zhe Gan Chunyuan Li Changyou Chen Yunchen Pu Qinliang Su Lawrence Carin BDL UQCV 251 42 0 23 Nov 2016
Stochastic Gradient MCMC with Stale Gradients Changyou Chen Nan Ding Chunyuan Li Yizhe Zhang Lawrence Carin BDL 187 23 0 21 Oct 2016
Relativistic Monte Carlo Xiaoyu Lu Valerio Perrone Leonard Hasenclever Yee Whye Teh Sebastian J. Vollmer BDL 138 39 0 14 Sep 2016
Stochastic Bouncy Particle Sampler Ari Pakman D. Gilboa David Carlson Liam Paninski 172 32 0 03 Sep 2016
A study of the effect of JPG compression on adversarial images Gintare Karolina Dziugaite Zoubin Ghahramani Daniel M. Roy AAML 227 581 0 02 Aug 2016
Stochastic Quasi-Newton Langevin Monte Carlo Umut Simsekli Roland Badeau A. Cemgil G. Richard BDL 220 63 0 10 Feb 2016
Distributed Bayesian Learning with Stochastic Natural-gradient Expectation Propagation and the Posterior Server Leonard Hasenclever Stefan Webb Thibaut Lienart Sebastian J. Vollmer Balaji Lakshminarayanan Charles Blundell Yee Whye Teh BDL 392 73 0 31 Dec 2015
Bridging the Gap between Stochastic Gradient MCMC and Stochastic Optimization Changyou Chen David Carlson Zhe Gan Chunyuan Li Lawrence Carin 195 92 0 25 Dec 2015
High-Order Stochastic Gradient Thermostats for Bayesian Learning of Deep Models Chunyuan Li Changyou Chen Kai Fan Lawrence Carin BDL 184 25 0 23 Dec 2015
Preconditioned Stochastic Gradient Descent Xi-Lin Li 208 106 0 14 Dec 2015
Adding Gradient Noise Improves Learning for Very Deep Networks Arvind Neelakantan Luke Vilnis Quoc V. Le Ilya Sutskever Lukasz Kaiser Karol Kurach James Martens AI4CE ODL 224 570 0 21 Nov 2015