中文
相关论文

相关论文: Online and Bandit Algorithms Beyond $\ell_p$ Norms

200 篇论文

Online learning algorithms are fast, memory-efficient, easy to implement, and applicable to many prediction problems, including classification, regression, and ranking. Several online algorithms were proposed in the past few decades, some…

机器学习 · 计算机科学 2015-07-03 Francesco Orabona , Koby Crammer , Nicolò Cesa-Bianchi

In this paper, we provide a rigorous proof of convergence of the Adaptive Moment Estimate (Adam) algorithm for a wide class of optimization objectives. Despite the popularity and efficiency of the Adam algorithm in training deep neural…

最优化与控制 · 数学 2023-11-08 Haochuan Li , Alexander Rakhlin , Ali Jadbabaie

Contextual multinomial logit (MNL) bandits capture many real-world assortment recommendation problems such as online retailing/advertising. However, prior work has only considered (generalized) linear value functions, which greatly limits…

机器学习 · 计算机科学 2024-02-20 Mengxiao Zhang , Haipeng Luo

Learning to rank is a supervised learning problem where the output space is the space of rankings but the supervision space is the space of relevance scores. We make theoretical contributions to the learning to rank problem both in the…

机器学习 · 计算机科学 2014-05-06 Sougata Chaudhuri , Ambuj Tewari

Multi-armed bandit problems are receiving a great deal of attention because they adequately formalize the exploration-exploitation trade-offs arising in several industrially relevant applications, such as online advertisement and, more…

机器学习 · 计算机科学 2013-11-05 Nicolò Cesa-Bianchi , Claudio Gentile , Giovanni Zappella

Many machine learning problems can be formulated as minimax problems such as Generative Adversarial Networks (GANs), AUC maximization and robust estimation, to mention but a few. A substantial amount of studies are devoted to studying the…

机器学习 · 计算机科学 2021-07-14 Yunwen Lei , Zhenhuan Yang , Tianbao Yang , Yiming Ying

We formulate a new problem at the intersectionof semi-supervised learning and contextual bandits,motivated by several applications including clini-cal trials and ad recommendations. We demonstratehow Graph Convolutional Network (GCN), a…

机器学习 · 计算机科学 2020-10-26 Sohini Upadhyay , Mikhail Yurochkin , Mayank Agarwal , Yasaman Khazaeni , DjallelBouneffouf

Collaborative bandit learning, i.e., bandit algorithms that utilize collaborative filtering techniques to improve sample efficiency in online interactive recommendation, has attracted much research attention as it enjoys the best of both…

机器学习 · 计算机科学 2021-04-16 Chuanhao Li , Qingyun Wu , Hongning Wang

Machine learning is a powerful method of extracting meaning from data; unfortunately, current digital hardware is extremely energy-intensive. There is interest in an alternative analog computing implementation that could match the…

机器学习 · 计算机科学 2026-02-17 Jonathan Lin , Aman Desai , Frank Barrows , Francesco Caravelli

It is shown the almost sure convergence and asymptotical normality of a generalization of Kesten's stochastic approximation algorithm for multidimensional case. In this generalization, the step increases or decreases if the scalar product…

统计理论 · 数学 2011-05-27 Pedro Cruz

We consider online learning with linear models, where the algorithm predicts on sequentially revealed instances (feature vectors), and is compared against the best linear function (comparator) in hindsight. Popular algorithms in this…

机器学习 · 计算机科学 2019-02-21 Michał Kempka , Wojciech Kotłowski , Manfred K. Warmuth

Most learning to rank research has assumed that the utility of different documents is independent, which results in learned ranking functions that return redundant results. The few approaches that avoid this have rather unsatisfyingly…

机器学习 · 计算机科学 2012-09-04 Aleksandrs Slivkins , Filip Radlinski , Sreenivas Gollapudi

We study bandit learning in matching markets with two-sided reward uncertainty, extending prior research primarily focused on single-sided uncertainty. Leveraging the concept of `super-stability' from Irving (1994), we demonstrate the…

机器学习 · 计算机科学 2025-06-23 Soumya Basu

In the stochastic online vector balancing problem, vectors $v_1,v_2,\ldots,v_T$ chosen independently from an arbitrary distribution in $\mathbb{R}^n$ arrive one-by-one and must be immediately given a $\pm$ sign. The goal is to keep the norm…

数据结构与算法 · 计算机科学 2020-07-22 Nikhil Bansal , Haotian Jiang , Raghu Meka , Sahil Singla , Makrand Sinha

In this paper, we analyze the problem of online convex optimization in different settings, including different feedback types (full-information/semi-bandit/bandit/etc) in either stochastic or non-stochastic setting and different notions of…

机器学习 · 计算机科学 2026-02-23 Mohammad Pedramfar , Vaneet Aggarwal

We use algorithmic methods from online learning to explore some important objects at the intersection of model theory and combinatorics, and find natural ways that algorithmic methods can detect and explain (and improve our understanding…

离散数学 · 计算机科学 2025-07-08 Maryanthe Malliaris , Shay Moran

Scaling test-time compute has emerged as an effective strategy for improving the performance of large language models. However, existing methods typically allocate compute uniformly across all queries, overlooking variation in query…

人工智能 · 计算机科学 2026-04-24 Bowen Zuo , Yinglun Zhu

Smooth functions on graphs have wide applications in manifold and semi-supervised learning. In this paper, we study a bandit problem where the payoffs of arms are smooth on a graph. This framework is suitable for solving online learning…

机器学习 · 统计学 2026-04-21 Michal Valko , Rémi Munos , Branislav Kveton , Tomáš Kocák

Gradient coding is a technique for straggler mitigation in distributed learning. In this paper we design novel gradient codes using tools from classical coding theory, namely, cyclic MDS codes, which compare favorably with existing…

信息论 · 计算机科学 2019-07-09 Netanel Raviv , Itzhak Tamo , Rashish Tandon , Alexandros G. Dimakis

Adaptive gradient methods have achieved remarkable success in training deep neural networks on a wide variety of tasks. However, not much is known about the mathematical and statistical properties of this family of methods. This work aims…

机器学习 · 计算机科学 2021-05-18 Zhang Zhiyi , Liu Ziyin