PulseAugur
中
实时 15:06:22

新研究探讨遗憾最小化和LLM偏好优化

作者 PulseAugur 编辑部 · [5 个来源] ·

本文介绍了一种新颖的框架，用于在线学习场景中具有分段线性奖励函数的遗憾最小化，适用于合同设计和拍卖等领域。在单调性假设下，所提出的算法实现了 $\widetilde{O}(\sqrt{nT})$ 的严格遗憾界限，解决了学习最优线性合同和在已发布价格拍卖中设定价格的开放性问题。此外，另一篇论文通过开发协方差遗憾泛函的导数理论来探索遗憾优化，并提出了在投资组合倾斜和基于LLM的分配策略中的应用。另一项研究侧重于LLM的偏好优化，提出了一种正则化技术以防止过度优化并提高生成质量，在Llama-3.1-8B-Instruct上取得了收益。 AI

影响 这些论文在优化和LLM对齐方面的理论理解上取得了进展，可能带来更高效、更可控的AI系统。

排序理由 多篇在arXiv上发表的学术论文，讨论了优化和LLM对齐方面的理论进展。

在 arXiv cs.LG 阅读 →

AI 生成摘要 · Google Gemini · 来自 5 个来源。 我们如何撰写摘要 →

新研究探讨遗憾最小化和LLM偏好优化

本文如何被排名

Signal score
0 / 100
Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket
Research
多篇在arXiv上发表的学术论文，讨论了优化和LLM对齐方面的理论进展。
Source corroboration
5 independent sources
Strong cross-source corroboration — multiple independent publishers covered this within the clustering window.
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
83 days old
Aged out of breaking-news scoring windows; ranking reflects the durable signal from the full source set.
Coverage growth since scoring
+1 source(s) since last score
New sources have picked up this story since our last re-score. Score will update on the next scoring pass.

完整方法见我们的编辑标准。

报道来源 [5]

  1. arXiv cs.LG TIER_1 English(EN) · Matteo Castiglioni, Anna Lunghi, Alberto Marchesi ·

    利用双维CDF打破后悔最小化的$T^{3/4}$障碍

    arXiv:2607.20258v1 Announce Type: new Abstract: We study regret minimization for learning CDF-related objectives of the form \[ g(x)\cdot\mathbb{P}_{X\sim\mathcal{D}}(X\le x), \] over $[0,1]^2$, where $g$ is a known Lipschitz function and $\mathcal{D}$ is an unknown distribution.…

  2. arXiv cs.LG TIER_1 Deutsch(DE) · Irene Aldridge ·

    优化遗憾

    arXiv:2607.18866v1 Announce Type: cross Abstract: Building on the identity that expected regret equals the covariance between costs and decisions, this paper develops the complete derivative theory of the covariance regret functional. We derive the G\^ateaux derivative, showing t…

  3. Hugging Face Daily Papers TIER_1 Deutsch(DE) ·

    优化遗憾

    Building on the identity that expected regret equals the covariance between costs and decisions, this paper develops the complete derivative theory of the covariance regret functional. We derive the Gâteaux derivative, showing that the universal steepest-descent direction is the …

  4. arXiv cs.AI TIER_1 English(EN) · Shawn Im, Federico Danieli, Skyler Seto, Barry-John Theobald, Katherine Metcalf ·

    偏好优化中的归一化奖励

    arXiv:2607.16240v1 Announce Type: cross Abstract: Direct Alignment Algorithms (DAAs) such as DPO have become a common way to post-train and align LLMs with human preferences. However, DAAs have been observed to over-optimize their implicit reward model and decrease the likelihood…

  5. arXiv cs.LG TIER_1 English(EN) · Francesco Bacchiocchi, Matteo Castiglioni, Alberto Marchesi, Nicola Gatti ·

    为分段线性奖励最小化遗憾：合同、拍卖及其他

    arXiv:2503.01701v2 Announce Type: replace-cross Abstract: Most microeconomic models of interest involve optimizing a piecewise linear function. These include contract design in hidden-action principal-agent problems, selling an item in posted-price auctions, and bidding in first-…

相关实体

相关话题