paper-with-me

Papers

Cyclical Stochastic Gradient MCMC for Bayesian Deep Learning

2019-02-11 · ICLR 2020 1 · Ruqi Zhang, Chunyuan Li, Jianyi Zhang, Changyou Chen, Andrew Gordon Wilson

The posteriors over neural network weights are high dimensional and multimodal. Each mode typically characterizes a meaningfully different representation of the data. We develop Cyclical Stochastic Gradient MCMC (SG-MCMC) to automatically explore such distributions. In particular, we propose a cyclical stepsize schedule, where larger steps discover new modes, and smaller steps characterize each mode. We also prove non-asymptotic convergence of our proposed algorithm. Moreover, we provide extensive experimental results, including ImageNet, to demonstrate the scalability and effectiveness of cyclical SG-MCMC in learning complex multimodal distributions, especially for fully Bayesian inference with modern deep neural networks.

📄 PDF Abstract BibTeX arXiv:1902.03932

Code (3)

ruqizhang/csgmcmc 공식 구현 pytorch
WayneDW/Contour-Stochastic-Gradient-Langevin-Dynamics
cobypenso/functional_ensemble_distillation pytorch

Tasks

Bayesian InferenceDeep LearningStochastic Optimization

Similar Papers 제목 키워드 기반

A Probabilistic Approach to Self-Supervised Learning using Cyclical Stochastic Gradient MCMC

2023-08-02 · Masoumeh Javanbakhat, Christoph Lippert

In this paper we present a practical Bayesian self-supervised learning method with Cyclical Stochastic Gradient Hamiltonian Monte Carlo (cSGHMC). Within this framework, we place a prior over the parameters of a self-supe…

Out-of-Distribution DetectionSelf-Supervised Learning

Learning to Explore for Stochastic Gradient MCMC

2024-08-17 · SeungHyun Kim, Seohyeon Jung, Seonghyeon Kim, Juho Lee

Bayesian Neural Networks(BNNs) with high-dimensional parameters pose a challenge for posterior inference due to the multi-modality of the posterior distributions. Stochastic Gradient MCMC(SGMCMC) with cyclical learning r…

image-classificationImage ClassificationMeta-LearningScheduling

Uncertainty Decomposition via Cyclical SG-MCMC and Soft-label Learning for Subjective NLP

2026-05-23 · Keito Inoshita, Takato Ueno arxiv

Annotator disagreement in emotion classification reflects ambiguity intrinsic to emotion concepts and is essential for predictor-quality assessment in subjective NLP. Yet no prior work integrates soft-label learning with…

Emotion Classification

Stochastic Gradient MCMC with Stale Gradients

2016-10-21 · NeurIPS 2016 12 · Changyou Chen, Nan Ding, Chunyuan Li, Yizhe Zhang 외

Stochastic gradient MCMC (SG-MCMC) has played an important role in large-scale Bayesian learning, with well-developed theoretical convergence properties. In such applications of SG-MCMC, it is becoming increasingly popul…

Extended Stochastic Gradient MCMC for Large-Scale Bayesian Variable Selection

2020-02-07 · Qifan Song, Yan Sun, Mao Ye, Faming Liang

Stochastic gradient Markov chain Monte Carlo (MCMC) algorithms have received much attention in Bayesian computing for big data problems, but they are only applicable to a small class of problems for which the parameter s…

Variable Selection