PulseAugur
中
实时 03:20:40

Federated Martingale Posterior sampling improves Bayesian neural networks

作者 PulseAugur 编辑部 · [2 个来源] ·

Researchers have introduced Federated Martingale Posterior (FMP) sampling, a novel protocol for federated Bayesian neural networks. This method addresses the difficulty of specifying priors in large models by using a predictive distribution and refitting. FMP sampling allows clients to upload data embeddings, enabling the server to run the predictive sampler centrally, thus avoiding the need to share local datasets. Experiments on standard datasets demonstrate that FMP closely matches centralized performance and offers improved calibration compared to existing consensus methods. AI

影响 Introduces a more efficient and calibrated approach for training Bayesian neural networks in federated settings, potentially improving privacy and accuracy.

排序理由 Publication of a new academic paper detailing a novel method in machine learning.

在 arXiv stat.ML 阅读 →

AI 生成摘要 · Google Gemini · 来自 2 个来源。 我们如何撰写摘要 →

Federated Martingale Posterior sampling improves Bayesian neural networks

报道来源 [2]

  1. arXiv stat.ML TIER_1 English(EN) · Boning Zhang, Matteo Zecchin, Mingzhao Guo, Dongzhu Liu, Osvaldo Simeone ·

    Federated Martingale Posterior Samping

    arXiv:2605.18554v1 Announce Type: cross Abstract: Federated Bayesian neural networks require fixing a prior on the model parameters together with a likelihood. Eliciting meaningful priors on the weight space of modern overparameterized models is notoriously difficult, and misspec…

  2. arXiv stat.ML TIER_1 English(EN) · Osvaldo Simeone ·

    Federated Martingale Posterior Samping

    Federated Bayesian neural networks require fixing a prior on the model parameters together with a likelihood. Eliciting meaningful priors on the weight space of modern overparameterized models is notoriously difficult, and misspecification of either component can severely degrade…

相关实体

相关话题