Pith. sign in

REVIEW 4 cited by

Cyclical Stochastic Gradient MCMC for Bayesian Deep Learning

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 1902.03932 v2 pith:EBCDQKJ3 submitted 2019-02-11 cs.LG cs.AIcs.CVstat.MEstat.ML

Ruqi Zhang , Chunyuan Li , Jianyi Zhang , Changyou Chen , Andrew Gordon Wilson This is my paper · ORCID
classification cs.LGcs.AIcs.CVstat.MEstat.ML
keywords cyclicalbayesiandeepdistributionsgradientlearningmcmcmode
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

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.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 4 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. Stochastic Weight Sharing for Bayesian Neural Networks

    cs.LG 2025-05 conditional novelty 6.0 of 10

    2DGBNN compresses Bayesian neural networks by clustering weight means and variances into shared 2D Gaussians, reducing parameter counts by up to 99% on ImageNet-scale models with small accuracy losses.

  2. Uncertainty-Driven Reliability: Selective Prediction and Trustworthy Deployment in Modern Machine Learning

    cs.LG 2025-08 conditional novelty 5.0 of 10

    A training-dynamics abstention method matches deep ensembles at a fraction of the training cost, and a five-term error budget explains why selective classifiers still fall short of the oracle.

  3. ConBatch-BAL: Batch Bayesian Active Learning under Budget Constraints

    cs.LG 2025-07 conditional novelty 4.0 of 10

    Two budget-aware batch active learning heuristics, greedy and dynamic thresholding, reduce the number of labeling rounds needed to reach target accuracy on new building image datasets compared with random selection.

  4. A Novel Active Learning Approach to Label One Million Unknown Malware Variants

    cs.CR 2025-06 reject novelty 3.0 of 10

    Proposes ViT-BNN for malware active learning with a tuned Gaussian scaling parameter, but results are not reproducible and the central claims are unsupported.

Pith tools