中文
相关论文

相关论文: Dual Averaging on Compactly-Supported Distribution…

200 篇论文

This paper develops projection-free algorithms for online convex optimization with stochastic constraints. We design an online primal-dual projection-free framework that can take any projection-free algorithms developed for online convex…

最优化与控制 · 数学 2023-05-17 Duksang Lee , Nam Ho-Nguyen , Dabeen Lee

Regularized online learning is widely used in machine learning applications. In online learning, performing exact minimization ($i.e.,$ implicit update) is known to be beneficial to the numerical stability and structure of solution. In this…

机器学习 · 计算机科学 2019-02-08 Chaobing Song , Ji Liu , Han Liu , Yong Jiang , Tong Zhang

We consider the problem of tracking the minimum of a time-varying convex optimization problem over a dynamic graph. Motivated by target tracking and parameter estimation problems in intermittently connected robotic and sensor networks, the…

最优化与控制 · 数学 2019-05-20 Rishabh Dixit , Amrit Singh Bedi , Ketan Rajawat

Distributionally Robust Optimization (DRO) is a popular framework for decision-making under uncertainty, but its adversarial nature can lead to overly conservative solutions. To address this, we study ex-ante Distributionally Robust Regret…

最优化与控制 · 数学 2025-04-22 Lukas-Benedikt Fiechtner , Jose Blanchet

We consider online optimization in the 1-lookahead setting, where the objective does not decompose additively over the rounds of the online game. The resulting formulation enables us to deal with non-stationary and/or long-term constraints…

机器学习 · 统计学 2016-06-09 Rodolphe Jenatton , Jim Huang , Dominik Csiba , Cedric Archambeau

This paper addresses safe distributed online optimization over an unknown set of linear safety constraints. A network of agents aims at jointly minimizing a global, time-varying function, which is only partially observable to each…

最优化与控制 · 数学 2023-02-27 Ting-Jui Chang , Sapana Chaudhary , Dileep Kalathil , Shahin Shahrampour

We define "decision swap regret" which generalizes both prediction for downstream swap regret and omniprediction, and give algorithms for obtaining it for arbitrary multi-dimensional Lipschitz loss functions in online adversarial settings.…

机器学习 · 计算机科学 2025-02-19 Jiuyao Lu , Aaron Roth , Mirah Shi

We provide an online learning algorithm that obtains regret $G\|w_\star\|\sqrt{T\log(\|w_\star\|G\sqrt{T})} + \|w_\star\|^2 + G^2$ on $G$-Lipschitz convex losses for any comparison point $w_\star$ without knowing either $G$ or…

机器学习 · 计算机科学 2024-06-03 Ashok Cutkosky , Zakaria Mhammedi

The goal of online prediction with expert advice is to find a decision strategy which will perform almost as well as the best expert in a given pool of experts, on any sequence of outcomes. This problem has been widely studied and…

机器学习 · 计算机科学 2018-05-22 Parameswaran Kamalaruban , Robert C. Williamson , Xinhua Zhang

We consider an online learning process to forecast a sequence of outcomes for nonconvex models. A typical measure to evaluate online learning algorithms is regret but such standard definition of regret is intractable for nonconvex models…

机器学习 · 计算机科学 2018-11-30 Sergul Aydore , Lee Dicker , Dean Foster

Making use of predictions is a crucial, but under-explored, area of online algorithms. This paper studies a class of online optimization problems where we have external noisy predictions available. We propose a stochastic prediction error…

机器学习 · 计算机科学 2015-04-28 Niangjun Chen , Anish Agarwal , Adam Wierman , Siddharth Barman , Lachlan L. H. Andrew

In this work, we study the online convex optimization problem with curved losses and delayed feedback. When losses are strongly convex, existing approaches obtain regret bounds of order $d_{\max} \ln T$, where $d_{\max}$ is the maximum…

机器学习 · 计算机科学 2025-06-10 Hao Qiu , Emmanuel Esposito , Mengxiao Zhang

We consider the problem of adversarial bandit convex optimization, that is, online learning over a sequence of arbitrary convex loss functions with only one function evaluation for each of them. While all previous works assume known and…

机器学习 · 计算机科学 2022-02-15 Haipeng Luo , Mengxiao Zhang , Peng Zhao

We consider online convex optimization when a number k of data points are outliers that may be corrupted. We model this by introducing the notion of robust regret, which measures the regret only on rounds that are not outliers. The aim for…

机器学习 · 计算机科学 2021-08-31 Tim van Erven , Sarah Sachs , Wouter M. Koolen , Wojciech Kotłowski

In this paper, we consider the problem of distributed online convex optimization, where a network of local agents aim to jointly optimize a convex function over a period of multiple time steps. The agents do not have any information about…

最优化与控制 · 数学 2019-11-13 Yan Zhang , Robert J. Ravier , Michael M. Zavlanos , Vahid Tarokh

We consider an online revenue maximization problem over a finite time horizon subject to lower and upper bounds on cost. At each period, an agent receives a context vector sampled i.i.d. from an unknown distribution and needs to make a…

机器学习 · 计算机科学 2021-04-21 Alfonso Lobos , Paul Grigas , Zheng Wen

To expand the applicability of decentralized online learning, previous studies have proposed several algorithms for decentralized online continuous submodular maximization (D-OCSM) -- a non-convex/non-concave setting with continuous…

机器学习 · 计算机科学 2026-02-11 Yuanyu Wan , Yu Shen , Dingzhi Yu , Bo Xue , Mingli Song

We consider the problem of transfer learning in an online setting. Different tasks are presented sequentially and processed by a within-task algorithm. We propose a lifelong learning strategy which refines the underlying data representation…

机器学习 · 统计学 2019-10-14 Pierre Alquier , The Tien Mai , Massimiliano Pontil

We study dynamic pricing where a seller repeatedly interacts with a strategic, non-myopic buyer who has a fixed private valuation and discounts future utility. Prior work focused exclusively on posted-price mechanisms, which only extract…

计算机科学与博弈论 · 计算机科学 2026-04-28 Shiliang Zuo

We develop parameter-free algorithms for unconstrained online learning with regret guarantees that scale with the gradient variation $V_T(u) = \sum_{t=2}^T \|\nabla f_t(u)-\nabla f_{t-1}(u)\|^2$. For $L$-smooth convex loss, we provide…

机器学习 · 计算机科学 2026-04-14 Yuheng Zhao , Andrew Jacobsen , Nicolò Cesa-Bianchi , Peng Zhao