mlsanityData to 7 Oct 2026

Federated Martingale Posterior Samping

arXiv 2605.18554 ↗First posted 18 May 2026cs.LG stat.MLcited by 0

Not on the map. Why?

Abstract (arXiv)

Federated Bayesian neural networks require fixing a prior on the model parameters, which is notoriously difficult, and misspecification of this prior can severely degrade accuracy and calibration. Motivated by the rapid progress of predictive models, the martingale posterior, also known as predictive Bayes, replaces the prior--likelihood pair with a predictive distribution and recovers parameter uncertainty by repeatedly drawing predictive samples and refitting the model. This letter proposes {federated martingale posterior} (FMP) sampling, a one-shot embarrassingly parallel protocol in which each client uploads a small set of trainable data embeddings and the server runs the predictive sampler centrally. Analysis of the sampling error demonstrates the impact of the dataset compression rate, while experiments show that FMP closely matches the centralized counterpart and achieves the lowest mean expected calibration error (ECE) among the evaluated one-shot federated methods.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 19 of its 24 references that are in the map. First posted on arXiv 18 May 2026.

Builds on

19 of 24 references.

References · 19

  1. 2017Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networkscited by 4,861
  2. 2017On Calibration of Modern Neural Networkscited by 4,860
  3. 2021On the Opportunities and Risks of Foundation Modelscited by 3,961
  4. 2016Variational Inference: A Review for Statisticianscited by 1,466
  5. 2019Measuring the Effects of Non-Identical Data Distribution for Federated Visual Classificationcited by 836
  6. 2013DeCAF: A Deep Convolutional Activation Feature for Generic Visual Recognitioncited by 422
  7. 2019Meta-Dataset: A Dataset of Datasets for Learning to Learn from Few Examplescited by 312
  8. 2013A General Framework for Updating Belief Distributionscited by 172
  9. 2019Functional Variational Bayesian Neural Networkscited by 127
  10. 2021Martingale posterior distributionscited by 43
  11. 2020Federated Generalized Bayesian Learning via Distributed Stein Variational Gradient Descentcited by 34
  12. 2023FedLPA: One-shot Federated Learning with Layer-Wise Posterior Aggregationcited by 22
7 more
  1. 2023Martingale Posterior Neural Processescited by 15
  2. 2023Federated Inference with Reliable Uncertainty Quantification over Wireless Channels via Conformal Predictioncited by 9
  3. 2022Robust PACm: Training Ensemble Models Under Misspecification and Outlierscited by 6
  4. 2025Bayesian Predictive Inference Beyond Martingalescited by 4
  5. 2024Bayesian Deep Learning Via Expectation Maximization and Turbo Deep Approximate Message Passingcited by 2
  6. 2025Uncertainty Quantification and Data Efficiency in AI: An Information-Theoretic Perspectivecited by 2
  7. 2024One-Shot Federated Learning with Bayesian Pseudocoresetscited by 1

Built on by

Not cited yet.