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
Adaptive Stepsizing for Stochastic Gradient Langevin Dynamics in Bayesian Neural Networks Rajit Rajpal Benedict Leimkuhler Yuanhao Jiang BDL 399 0 0 11 Nov 2025
Compressibility Measures Complexity: Minimum Description Length Meets Singular Learning Theory Einar Urdshals Edmund Lau Jesse Hoogland Stan van Wingerden Daniel Murfet 103 1 0 14 Oct 2025
Influence Dynamics and Stagewise Data Attribution Jin Hwa Lee Matthew Smith Maxwell Adam Jesse Hoogland TDI AI4TS 177 0 0 14 Oct 2025
Flatness-Aware Stochastic Gradient Langevin Dynamics Stefano Bruno Youngsik Hwang Jaehyeon An Sotirios Sabanis Dong-Young Lim 152 0 0 02 Oct 2025
Bayesian Influence Functions for Hessian-Free Data Attribution Philipp Alexander Kreer Wilson Wu Maxwell Adam Zach Furman Jesse Hoogland TDI BDL 203 2 0 30 Sep 2025
Two Birds with One Stone: Enhancing Uncertainty Quantification and Interpretability with Graph Functional Neural ProcessInternational Conference on Artificial Intelligence and Statistics (AISTATS), 2025 Lingkai Kong Haotian Sun Yuchen Zhuang Haorui Wang Wenhao Mu Chao Zhang BDL 148 5 0 23 Aug 2025
From Global to Local: A Scalable Benchmark for Local Posterior Sampling Rohan Hitchcock Jesse Hoogland 138 1 0 29 Jul 2025
Feel-Good Thompson Sampling for Contextual Bandits: a Markov Chain Monte Carlo Showdown Emile Anand Sarah Liaw 212 0 0 21 Jul 2025
Conformal Object Detection by Sequential Risk Control Léo Andéol Luca Mossina Adrien Mazoyer Sébastien Gerchinovitz 324 0 0 29 May 2025
Enhancing Uncertainty Estimation and Interpretability via Bayesian Non-negative Decision LayerInternational Conference on Learning Representations (ICLR), 2025 Xinyue Hu Zhibin Duan Bo Chen Mingyuan Zhou UQCV BDL 332 2 0 28 May 2025
Training Latent Diffusion Models with Interacting Particle Algorithms Tim Y. J. Wang Juan Kuntz O. Deniz Akyildiz 413 3 0 18 May 2025
JaxSGMC: Modular stochastic gradient MCMC in JAXSoftwareX (SoftwareX), 2024 Stephan Thaler Paul Fuchs Ana Cukarska Julija Zavadlav BDL 408 2 0 16 May 2025
Cooperative Bayesian and variance networks disentangle aleatoric and epistemic uncertainties Jiaxiang Yi Miguel A. Bessa UD PER UQCV 317 2 0 05 May 2025
Parameter Expanded Stochastic Gradient Markov Chain Monte CarloInternational Conference on Learning Representations (ICLR), 2025 Hyunsu Kim G. Nam Chulhee Yun Hongseok Yang Juho Lee BDL UQCV 237 0 0 02 Mar 2025
Bayesian Computation in Deep Learning Wenlong Chen Bolian Li Ruqi Zhang Yingzhen Li BDL 476 1 0 25 Feb 2025
Muti-Fidelity Prediction and Uncertainty Quantification with Laplace Neural Operators for Parametric Partial Differential Equations Haoyang Zheng Guang Lin AI4CE 192 1 0 01 Feb 2025
Stochastic Process Learning via Operator Flow Matching Yaozhong Shi Zachary E. Ross D. Asimaki Kamyar Azizzadenesheli 506 5 0 07 Jan 2025
BayesNAM: Leveraging Inconsistency for Reliable Explanations Hoki Kim Jinseong Park Yujin Choi Seungyun Lee Jaewook Lee BDL 145 1 0 10 Nov 2024
Gradient Methods with Online ScalingAnnual Conference Computational Learning Theory (COLT), 2024 Wenzhi Gao Ya-Chi Chu Yinyu Ye Madeleine Udell 287 13 0 04 Nov 2024
Functional Stochastic Gradient MCMC for Bayesian Neural NetworksInternational Conference on Artificial Intelligence and Statistics (AISTATS), 2024 Mengjing Wu Junyu Xuan Jie Lu BDL 271 1 0 25 Sep 2024
Learning to Explore for Stochastic Gradient MCMCInternational Conference on Machine Learning (ICML), 2024 Seunghyun Kim Seohyeon Jung Seonghyeon Kim Juho Lee BDL 270 1 0 17 Aug 2024
Particle Semi-Implicit Variational Inference Jen Ning Lim A. M. Johansen 359 11 0 30 Jun 2024
Reparameterization invariance in approximate Bayesian inference Hrittik Roy M. Miani Carl Henrik Ek Philipp Hennig Marvin Pfortner Lukas Tatzel Søren Hauberg BDL 325 14 0 05 Jun 2024
Scalable Bayesian Learning with posteriors Samuel Duffield Kaelan Donatella Johnathan Chiu Phoebe Klett Daniel Simpson BDL UQCV 496 4 0 31 May 2024
Taming Score-Based Diffusion Priors for Infinite-Dimensional Nonlinear Inverse Problems Lorenzo Baldassari Ali Siahkoohi Josselin Garnier K. Sølna Maarten V. de Hoop DiffM 300 3 0 24 May 2024
Stochastic Gradient MCMC for Massive Geostatistical Data M. Abba Brian J. Reich Reetam Majumder Brandon Feng 177 1 0 07 May 2024
NPB-REC: A Non-parametric Bayesian Deep-learning Approach for Undersampled MRI Reconstruction with Uncertainty Estimation Samah Khawaled Moti Freiman UQCV 158 5 0 06 Apr 2024
Fast Value Tracking for Deep Reinforcement Learning Frank Shih Faming Liang BDL 113 4 0 19 Mar 2024
On the Convergence of Locally Adaptive and Scalable Diffusion-Based Sampling Methods for Deep Bayesian Neural Network PosteriorsInternational Conference on Artificial Intelligence and Statistics (AISTATS), 2024 Tim Rensmeyer Oliver Niggemann UQCV BDL OOD MedIm 155 1 0 13 Mar 2024
Improving Implicit Regularization of SGD with Preconditioning for Least Square Problems Junwei Su Difan Zou Chuan Wu 384 0 0 13 Mar 2024
Scalable Bayesian inference for the generalized linear mixed model S. Berchuck Felipe A. Medeiros Sayan Mukherjee Andrea Agazzi 182 0 0 05 Mar 2024
Scaling up Dynamic Edge Partition Models via Stochastic Gradient MCMC Sikun Yang Heinz Koeppl 193 0 0 29 Feb 2024
Weight fluctuations in (deep) linear neural networks and a derivation of the inverse-variance flatness relationPhysical Review Research (Phys. Rev. Res.), 2023 Markus Gross A. Raulf Christoph Räth 420 0 0 23 Nov 2023
Bayesian Domain Invariant Learning via Posterior Generalization of Parameter Distributions Shiyu Shen Bin Pan Tianyang Shi Tao Li Zhenwei Shi BDL OOD 260 1 0 25 Oct 2023
Be Bayesian by Attachments to Catch More Uncertainty Shiyu Shen Bin Pan Tianyang Shi Tao Li Zhenwei Shi UQCV 290 0 0 19 Oct 2023
The surrogate Gibbs-posterior of a corrected stochastic MALA: Towards uncertainty quantification for neural networks S. Bieringer Gregor Kasieczka Maximilian F. Steffen Mathias Trabs 294 0 0 13 Oct 2023
A Primer on Bayesian Neural Networks: Review and Debates Federico Danieli Konstantinos Pitas M. Vladimirova Vincent Fortuin BDL AAML 243 34 0 28 Sep 2023
A Probabilistic Approach to Self-Supervised Learning using Cyclical Stochastic Gradient MCMC Masoumeh Javanbakhat Christoph Lippert SSL BDL 100 1 0 02 Aug 2023
BayesDAG: Gradient-Based Posterior Inference for Causal DiscoveryNeural Information Processing Systems (NeurIPS), 2023 Yashas Annadani Nick Pawlowski Joel Jennings Stefan Bauer Cheng Zhang Wenbo Gong CML BDL 248 30 0 26 Jul 2023
High-Rate Phase Association with Travel Time Neural Fields Chengzhi Shi Maarten V. de Hoop Ivan Dokmanić 235 1 0 14 Jul 2023
Quantification of Uncertainty with Adversarial ModelsNeural Information Processing Systems (NeurIPS), 2023 Kajetan Schweighofer L. Aichberger Mykyta Ielanskyi Günter Klambauer Sepp Hochreiter UQCV 262 28 0 06 Jul 2023
MAT: Mixed-Strategy Game of Adversarial Training in Fine-tuningInternational Joint Conference on Artificial Intelligence (IJCAI), 2023 Zhehua Zhong Tianyi Chen Zhen Wang AAML 119 4 0 27 Jun 2023
A New Paradigm for Generative Adversarial Networks based on Randomized Decision RulesStatistica sinica (Stat. Sinica), 2023 Sehwan Kim Qifan Song Faming Liang GAN 94 1 0 23 Jun 2023
Fit Like You Sample: Sample-Efficient Generalized Score Matching from Fast Mixing DiffusionsAnnual Conference Computational Learning Theory (COLT), 2023 Yilong Qin Andrej Risteski DiffM 313 2 0 15 Jun 2023
Gibbs Sampling the Posterior of Neural Networks Giovanni Piccioli Emanuele Troiani Lenka Zdeborová 205 3 0 05 Jun 2023
A General Framework for Uncertainty Quantification via Neural SDE-RNN Shweta Dahale Sai Munikoti Balasubramaniam Natarajan AI4TS UQCV BDL 128 3 0 01 Jun 2023
Provable and Practical: Efficient Exploration in Reinforcement Learning via Langevin Monte CarloInternational Conference on Learning Representations (ICLR), 2023 Haque Ishfaq Qingfeng Lan Pan Xu A. R. Mahmood Doina Precup Anima Anandkumar Kamyar Azizzadenesheli BDL OffRL 312 27 0 29 May 2023
Non-Log-Concave and Nonsmooth Sampling via Langevin Monte Carlo Algorithms Tim Tsz-Kit Lau Han Liu Thomas Pock 366 7 0 25 May 2023
Tuning-Free Maximum Likelihood Training of Latent Variable Models via Coin BettingInternational Conference on Artificial Intelligence and Statistics (AISTATS), 2023 Louis Sharrock Daniel Dodd Christopher Nemeth 214 10 0 24 May 2023
Particle Mean Field Variational Bayes Minh-Ngoc Tran Paco Tseng Robert Kohn 249 4 0 24 Mar 2023