English(EN) Non-Ergodic Markovian Mirror Descent with Unbounded Noise

一项新研究详细介绍了具有无界噪声的非遍历马尔可夫镜像下降法

作者 PulseAugur 编辑部 · [1 个来源] · 2026-10-28 04:00

研究人员 Yunus Alp Biyikoglu 和 arXiv 发表了一篇新论文，详细介绍了一种分析随机镜像下降法的方法。他们的工作侧重于在马尔可夫链中最小化凸目标，利用来自单个样本路径的有噪声次梯度观测。该论文为加权平均迭代的次优性差距建立了 O(T^{-1/2}) 的界限，即使在具有无界随机次梯度和泊松解的情况下也是如此。只要满足某些正则性和矩条件，这种分析就适用于有限状态和不可约可数状态的马尔可夫链。 AI

影响为与机器学习相关的优化技术提供了理论进展。

排序理由关于优化算法的学术论文。[lever_c_demoted from research: ic=1 ai=0.7]

在 arXiv cs.LG 阅读 →

AI 生成摘要 · Google Gemini · 来自 1 个来源。我们如何撰写摘要 →

本文如何被排名

Signal score: 11 / 100; Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket: Tool; 关于优化算法的学术论文。[lever_c_demoted from research: ic=1 ai=0.7]
Source corroboration: Single-source cluster; Only one publisher covered this so far. Single-source stories can still rank when the publisher is high-authority, but they lack cross-source corroboration.
Topics: paper, other; Editorial topic classification. Feeds into how the story surfaces on /topic/<slug> hub pages and into the per-entity coverage mix.
AI-industry relevance: High; Clearly on-topic for AI-industry coverage.
Story freshness: Breaking (< 6h); Fresh story with cross-source coverage still developing. Ranking may shift as more sources report.

完整方法见我们的编辑标准。

报道来源 [1]

arXiv cs.LG TIER_1 English(EN) · Yunus Alp Biyikoglu, R. Srikant · 2026-10-28 04:00

具有无界噪声的非遍历马尔可夫镜像下降法

arXiv:2610.34433v1 Announce Type: cross Abstract: We analyze stochastic mirror descent for minimizing a convex objective expressed as an expectation under the stationary distribution of a Markov chain, using noisy subgradient observations along a single sample path. Through Poiss…

本文如何被排名

报道来源 [1]

具有无界噪声的非遍历马尔可夫镜像下降法

相关实体

相关话题