arXivDaily arXiv每日学术速递 周一至周五更新

期刊&会议

NeurIPS

Conference on Neural Information Processing Systems · 会议 · Machine Learning

2026-06-26 至 2026-06-26 共收录 3
2606.26601 2026-06-26 cs.SI 新提交

Fast Computation and Optimization for Opinion-Based Quantities of Friedkin-Johnsen Model

Friedkin-Johnsen模型中基于意见的量的快速计算与优化

Haoxin Sun, Yubo Sun, Xiaotian Zhou, Zhongzhi Zhang

AI总结 针对FJ模型,提出基于部分有根森林的高效算法计算意见相关量,并用于意见最小化及极化与分歧最小化问题,将时间复杂度从线性降至亚线性。

Comments Published at NeurIPS 2025

详情

展开后加载摘要…

URL PDF HTML 收藏
2605.20919 2026-06-26 cs.LG cs.AI cs.PL 版本更新

Sutra: Tensor-Op RNNs as a Compilation Target for Vector Symbolic Architectures

Sutra: 以张量操作RNN作为向量符号架构的编译目标

Emma Leonhart

机构 * Emma Leonhart

AI总结 Sutra是一种纯函数式编程语言,通过编译将整个程序降级为融合张量操作图,同时支持符号推理和神经网络训练,实现逻辑程序与可训练网络的统一。

Comments Modified NeurIPS submission, see AI declaration and replication materials at end of paper

详情

展开后加载摘要…

URL PDF HTML 收藏
2409.01447 2026-06-26 cs.LG cs.GT 版本更新

Decentralized Best-Response-Based Learning in Two-Player Zero-Sum Stochastic Games: A Finite-Sample Analysis

两人零和随机博弈中基于最优响应的去中心化学习:有限样本分析

Zaiwei Chen, Kaiqing Zhang, Eric Mazumdar, Asuman Ozdaglar, Adam Wierman

机构 * Purdue University(普渡大学) University of Maryland, College Park(马里兰大学学院公园分校) Caltech(加州理工学院) MIT(麻省理工学院)

AI总结 本文对两人零和矩阵博弈和随机博弈中的去中心化学习进行有限样本分析,提出基于最优响应的学习算法,并证明其样本复杂度。

Comments A preliminary version [arXiv:2303.03100] of this paper, with a subset of the results that are presented here, was presented at NeurIPS 2023

详情

展开后加载摘要…

URL PDF HTML 收藏