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"

50 / 189 papers shown

Title
Scalable Stochastic Gradient Riemannian Langevin Dynamics in Non-Diagonal Metrics Hanlin Yu M. Hartmann Bernardo Williams Arto Klami BDL 323 9 0 09 Mar 2023
Gradient-based Wang-Landau Algorithm: A Novel Sampler for Output Distribution of Neural Networks over the Input SpaceInternational Conference on Machine Learning (ICML), 2023 Weitang Liu Ying-Wai Li Yi-Zhuang You Jingbo Shang 119 2 0 19 Feb 2023
Piecewise Deterministic Markov Processes for Bayesian Neural NetworksConference on Uncertainty in Artificial Intelligence (UAI), 2023 Ethan Goan Dimitri Perrin Kerrie Mengersen Clinton Fookes 175 0 0 17 Feb 2023
Preconditioned Score-based Generative ModelsInternational Journal of Computer Vision (IJCV), 2023 He Ma Xiatian Zhu Xiatian Zhu Jianfeng Feng DiffM 241 7 0 13 Feb 2023
Langevin algorithms for very deep Neural Networks with application to image classification Pierre Bras 151 6 0 27 Dec 2022
Langevin algorithms for Markovian Neural Networks and Deep Stochastic controlIEEE International Joint Conference on Neural Network (IJCNN), 2022 Pierre Bras Gilles Pagès 156 6 0 22 Dec 2022
Scalable Bayesian Uncertainty Quantification for Neural Network Potentials: Promise and PitfallsJournal of Chemical Theory and Computation (JCTC), 2022 Stephan Thaler Gregor Doehner Julija Zavadlav 245 24 0 15 Dec 2022
Effects of Spectral Normalization in Multi-agent Reinforcement LearningIEEE International Joint Conference on Neural Network (IJCNN), 2022 K. Mehta Anuj Mahajan Kiran Ravish 213 11 0 10 Dec 2022
PAC-Bayes Bounds for Bandit Problems: A Survey and Experimental ComparisonIEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2022 H. Flynn David Reeb M. Kandemir Jan Peters OffRL 274 7 0 29 Nov 2022
Particle-based Variational Inference with Preconditioned Functional Gradient FlowInternational Conference on Learning Representations (ICLR), 2022 Hanze Dong Xi Wang Yong Lin Tong Zhang 195 21 0 25 Nov 2022
Non-reversible Parallel Tempering for Deep Posterior ApproximationAAAI Conference on Artificial Intelligence (AAAI), 2022 Wei Deng Qian Zhang Qi Feng F. Liang Guang Lin 217 4 0 20 Nov 2022
Federated Averaging Langevin Dynamics: Toward a unified theory and new algorithmsInternational Conference on Artificial Intelligence and Statistics (AISTATS), 2022 Vincent Plassier Alain Durmus Eric Moulines FedML 354 7 0 31 Oct 2022
Reliable amortized variational inference with physics-based latent distribution correction Ali Siahkoohi G. Rizzuti Rafael Orozco Felix J. Herrmann 231 32 0 24 Jul 2022
Automatic differentiation and the optimization of differential equation models in biologyFrontiers in Ecology and Evolution (Front. Ecol. Evol.), 2022 S. Frank 129 6 0 10 Jul 2022
Accelerating Score-based Generative Models with Preconditioned Diffusion SamplingEuropean Conference on Computer Vision (ECCV), 2022 He Ma Li Zhang Xiatian Zhu Jianfeng Feng DiffM 189 30 0 05 Jul 2022
A Langevin-like Sampler for Discrete DistributionsInternational Conference on Machine Learning (ICML), 2022 Ruqi Zhang Xingchao Liu Qiang Liu BDL 155 46 0 20 Jun 2022
Benchmarking Bayesian neural networks and evaluation metrics for regression tasks B. Staber Sébastien Da Veiga UQCV BDL 226 3 0 08 Jun 2022
Masked Bayesian Neural Networks : Computation and Optimality Insung Kong Dongyoon Yang Jongjin Lee Ilsang Ohn Yongdai Kim TPM 250 1 0 02 Jun 2022
How Tempering Fixes Data Augmentation in Bayesian Neural NetworksInternational Conference on Machine Learning (ICML), 2022 Gregor Bachmann Lorenzo Noci Thomas Hofmann BDL AAML 229 11 0 27 May 2022
The Sufficiency of Off-Policyness and Soft Clipping: PPO is still Insufficient according to an Off-Policy MeasureAAAI Conference on Artificial Intelligence (AAAI), 2022 Xing Chen Dongcui Diao Hechang Chen Hengshuai Yao Haiyin Piao Zhixiao Sun Zhiwei Yang Randy Goebel Bei Jiang Yi-Ju Chang OffRL 369 23 0 20 May 2022
A Survey on Uncertainty Toolkits for Deep Learning Maximilian Pintz Joachim Sicking Maximilian Poretschkin Maram Akila ELM 245 7 0 02 May 2022
Optimizing differential equations to fit data and predict outcomesEcology and Evolution (Ecol Evol), 2022 S. Frank 80 4 0 16 Apr 2022
VFDS: Variational Foresight Dynamic Selection in Bayesian Neural Networks for Efficient Human Activity RecognitionInternational Conference on Artificial Intelligence and Statistics (AISTATS), 2022 Randy Ardywibowo Shahin Boluki Zinan Lin Bobak J. Mortazavi Shuai Huang Xiaoning Qian 157 2 0 31 Mar 2022
DiSECt: A Differentiable Simulator for Parameter Inference and Control in Robotic CuttingAutonomous Robots (AR), 2022 Eric Heiden Lukasz Wawrzyniak Yashraj S. Narang Dieter Fox Animesh Garg Fabio Ramos 253 13 0 19 Mar 2022
PAC-Bayesian Lifelong Learning For Multi-Armed BanditsData mining and knowledge discovery (DMKD), 2022 H. Flynn David Reeb M. Kandemir Jan Peters 182 8 0 07 Mar 2022
Interacting Contour Stochastic Gradient Langevin DynamicsInternational Conference on Learning Representations (ICLR), 2022 Wei Deng Siqi Liang Botao Hao Guang Lin F. Liang BDL 174 12 0 20 Feb 2022
Nonlinear MCMC for Bayesian Machine LearningNeural Information Processing Systems (NeurIPS), 2022 James Vuckovic 175 3 0 11 Feb 2022
Scalable Batch-Mode Deep Bayesian Active Learning via Equivalence Class AnnealingInternational Conference on Learning Representations (ICLR), 2021 Renyu Zhang Aly A. Khan Robert L. Grossman Yuxin Chen BDL 209 4 0 27 Dec 2021
Approximate Inference via Clustering Qianqian Song 174 0 0 28 Nov 2021
Unsupervised PET Reconstruction from a Bayesian PerspectiveIEEE International Symposium on Biomedical Imaging (ISBI), 2021 Chenyu Shen Wenjun Xia H. Ye Mingzheng Hou Hu Chen Yan Liu Jiliu Zhou Yi Zhang 187 3 0 29 Oct 2021
Deep Bayesian inference for seismic imaging with tasks Ali Siahkoohi G. Rizzuti Felix J. Herrmann BDL UQCV 333 23 0 10 Oct 2021
A fast asynchronous MCMC sampler for sparse Bayesian inference Yves F. Atchadé Liwei Wang 126 3 0 14 Aug 2021
Batch Normalization Preconditioning for Neural Network Training Susanna Lange Kyle E. Helfrich Qiang Ye 197 13 0 02 Aug 2021
Structured Stochastic Gradient MCMCInternational Conference on Machine Learning (ICML), 2021 Antonios Alexos Alex Boyd Stephan Mandt BDL 223 13 0 19 Jul 2021
Differentially Private Bayesian Neural Networks on Accuracy, Privacy and Reliability Qiyiwen Zhang Zhiqi Bu Kan Chen Qi Long BDL UQCV 194 12 0 18 Jul 2021
A Survey of Uncertainty in Deep Neural Networks J. Gawlikowski Cedrique Rovile Njieutcheu Tassi Mohsin Ali Jongseo Lee Matthias Humt ... R. Roscher Muhammad Shahzad Wen Yang R. Bamler Xiaoxiang Zhu BDL UQCV OOD 527 1,459 0 07 Jul 2021
Sampling with Mirrored Stein Operators Jiaxin Shi Chang-rui Liu Lester W. Mackey 334 21 0 23 Jun 2021
Disentangling the Roles of Curation, Data-Augmentation and the Prior in the Cold Posterior EffectNeural Information Processing Systems (NeurIPS), 2021 Lorenzo Noci Kevin Roth Gregor Bachmann Sebastian Nowozin Thomas Hofmann CML 198 26 0 11 Jun 2021
When in Doubt: Neural Non-Parametric Uncertainty Quantification for Epidemic ForecastingNeural Information Processing Systems (NeurIPS), 2021 Harshavardhan Kamarthi Lingkai Kong Alexander Rodríguez Chao Zhang B. Prakash AI4TS BDL 227 25 0 07 Jun 2021
Asymptotics of representation learning in finite Bayesian neural networksNeural Information Processing Systems (NeurIPS), 2021 Jacob A. Zavatone-Veth Abdulkadir Canatar Benjamin S. Ruben Cengiz Pehlevan 357 36 0 01 Jun 2021
Efficient and Generalizable Tuning Strategies for Stochastic Gradient MCMCStatistics and computing (Stat Comput), 2021 Jeremie Coullon Leah F. South Christopher Nemeth 222 13 0 27 May 2021
DiSECt: A Differentiable Simulation Engine for Autonomous Robotic Cutting Eric Heiden Lukasz Wawrzyniak Yashraj S. Narang Dieter Fox Animesh Garg Fabio Ramos 210 107 0 25 May 2021
Contextual Dropout: An Efficient Sample-Dependent Dropout ModuleInternational Conference on Learning Representations (ICLR), 2021 Xinjie Fan Shujian Zhang Korawat Tanwisuth Xiaoning Qian Mingyuan Zhou OOD BDL UQCV 160 31 0 06 Mar 2021
Generalization Bounds for Noisy Iterative Algorithms Using Properties of Additive Noise ChannelsJournal of machine learning research (JMLR), 2021 Hao Wang Rui Gao Flavio du Pin Calmon 274 20 0 05 Feb 2021
Unadjusted Langevin algorithm with multiplicative noise: Total variation and Wasserstein boundsThe Annals of Applied Probability (Ann. Appl. Probab.), 2020 Gilles Pagès Fabien Panloup 120 28 0 28 Dec 2020
EVA: Generating Longitudinal Electronic Health Records Using Conditional Variational AutoencodersMachine Learning in Health Care (MLHC), 2020 Siddharth Biswal S. Ghosh J. Duke B. Malin Walter F. Stewart Jimeng Sun SyDa BDL DRL 227 45 0 18 Dec 2020
Bayesian Neural Ordinary Differential Equations Raj Dandekar Karen Chung Vaibhav Dixit Mohamed Tarek Aslan Garcia-Valadez Krishna Vishal Vemula Chris Rackauckas UQCV OOD BDL 325 60 0 14 Dec 2020
Efficient and Transferable Adversarial Examples from Bayesian Neural Networks Martin Gubri Maxime Cordy Mike Papadakis Yves Le Traon Koushik Sen AAML 319 12 0 10 Nov 2020
On the Ergodicity, Bias and Asymptotic Normality of Randomized Midpoint Sampling Method Ye He Krishnakumar Balasubramanian Murat A. Erdogdu 217 40 0 06 Nov 2020
A Contour Stochastic Gradient Langevin Dynamics Algorithm for Simulations of Multi-modal DistributionsNeural Information Processing Systems (NeurIPS), 2020 Wei Deng Guang Lin F. Liang BDL 292 33 0 19 Oct 2020