中文
相关论文

相关论文: On the Regret Minimization of Nonconvex Online Gra…

200 篇论文

We analyze and evaluate an online gradient descent algorithm with adaptive per-coordinate adjustment of learning rates. Our algorithm can be thought of as an online version of batch gradient descent with a diagonal preconditioner. This…

机器学习 · 计算机科学 2010-02-26 Matthew Streeter , H. Brendan McMahan

Motivated by applications in machine learning and operations research, we study regret minimization with stochastic first-order oracle feedback in online constrained, and possibly non-smooth, non-convex problems. In this setting, the…

机器学习 · 计算机科学 2020-10-14 Nadav Hallak , Panayotis Mertikopoulos , Volkan Cevher

We introduce an online convex optimization algorithm which utilizes projected subgradient descent with optimal adaptive learning rates. Our method provides second-order minimax-optimal dynamic regret guarantee (i.e. dependent on the sum of…

最优化与控制 · 数学 2022-09-14 Hakan Gokcesu , Suleyman S. Kozat

We investigate online convex optimization in non-stationary environments and choose dynamic regret as the performance measure, defined as the difference between cumulative loss incurred by the online algorithm and that of any feasible…

机器学习 · 计算机科学 2024-04-09 Peng Zhao , Yu-Jie Zhang , Lijun Zhang , Zhi-Hua Zhou

Stochastic and adversarial data are two widely studied settings in online learning. But many optimization tasks are neither i.i.d. nor fully adversarial, which makes it of fundamental interest to get a better theoretical understanding of…

机器学习 · 计算机科学 2022-06-09 Sarah Sachs , Hédi Hadiji , Tim van Erven , Cristóbal Guzmán

Learning and computation of equilibria are central problems in game theory, theory of computation, and artificial intelligence. In this work, we introduce proximal regret, a new notion of regret based on proximal operators that lies…

计算机科学与博弈论 · 计算机科学 2025-11-06 Yang Cai , Constantinos Daskalakis , Haipeng Luo , Chen-Yu Wei , Weiqiang Zheng

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 study online convex optimization under stochastic sub-gradient observation faults, where we introduce adaptive algorithms with minimax optimal regret guarantees. We specifically study scenarios where our sub-gradient observations can be…

机器学习 · 计算机科学 2019-04-23 Hakan Gokcesu , Suleyman S. Kozat

Stochastic and adversarial data are two widely studied settings in online learning. But many optimization tasks are neither i.i.d. nor fully adversarial, which makes it of fundamental interest to get a better theoretical understanding of…

机器学习 · 计算机科学 2025-11-03 Sarah Sachs , Hedi Hadiji , Tim van Erven , Cristobal Guzman

We study an algorithmic equivalence technique between non-convex gradient descent and convex mirror descent. We start by looking at a harder problem of regret minimization in online non-convex optimization. We show that under certain…

机器学习 · 计算机科学 2022-10-14 Udaya Ghai , Zhou Lu , Elad Hazan

This paper studies online nonstochastic control problems with adversarial and static constraints. We propose online nonstochastic control algorithms that achieve both sublinear regret and sublinear adversarial constraint violation while…

机器学习 · 计算机科学 2023-02-07 Xin Liu , Zixian Yang , Lei Ying

This paper addresses an online convex optimization problem where the cost function at each step depends on a history of past decisions (i.e., memory), and the decision maker has access to limited predictions of future cost values within a…

最优化与控制 · 数学 2025-12-29 Zhengmiao Wang , Zhi-Wei Liu , Ming Chi , Xiaoling Wang , Housheng Su , Lintao Ye

We propose algorithms for online principal component analysis (PCA) and variance minimization for adaptive settings. Previous literature has focused on upper bounding the static adversarial regret, whose comparator is the optimal fixed…

机器学习 · 计算机科学 2019-05-14 Jianjun Yuan , Andrew Lamperski

We study online learning with bandit feedback (i.e. learner has access to only zeroth-order oracle) where cost/reward functions $\f_t$ admit a "pseudo-1d" structure, i.e. $\f_t(\w) = \loss_t(\pred_t(\w))$ where the output of $\pred_t$ is…

机器学习 · 计算机科学 2021-02-16 Aadirupa Saha , Nagarajan Natarajan , Praneeth Netrapalli , Prateek Jain

We consider the framework of non-stationary Online Convex Optimization where a learner seeks to control its dynamic regret against an arbitrary sequence of comparators. When the loss functions are strongly convex or exp-concave, we…

机器学习 · 计算机科学 2021-11-24 Dheeraj Baby , Hilaf Hasson , Yuyang Wang

This paper considers the distributed online convex-concave optimization with constraint sets over a multiagent network, in which each agent autonomously generates a series of decision pairs through a designable mechanism to cooperatively…

最优化与控制 · 数学 2025-08-14 Wentao Zhang , Baoyong Zhang , Deming Yuan , Shengyuan Xu , Vincent K. N. Lau

Adaptive gradient algorithms such as ADAGRAD and its variants have gained popularity in the training of deep neural networks. While many works as for adaptive methods have focused on the static regret as a performance metric to achieve a…

机器学习 · 计算机科学 2022-09-07 Parvin Nazari , Esmaile Khorram

In this paper, we consider the problem of distributed online convex optimization, where a group of agents collaborate to track the global minimizers of a sum of time-varying objective functions in an online manner. Specifically, we propose…

最优化与控制 · 数学 2020-10-14 Yan Zhang , Robert J. Ravier , Vahid Tarokh , Michael M. Zavlanos

The need for fast and robust optimization algorithms are of critical importance in all areas of machine learning. This paper treats the task of designing optimization algorithms as an optimal control problem. Using regret as a metric for an…

机器学习 · 计算机科学 2021-01-21 Philippe Casgrain , Anastasis Kratsios

We provide an online convex optimization algorithm with regret that interpolates between the regret of an algorithm using an optimal preconditioning matrix and one using a diagonal preconditioning matrix. Our regret bound is never worse…

机器学习 · 计算机科学 2019-05-31 Ashok Cutkosky , Tamas Sarlos
‹ 上一页 1 2 3 10 下一页 ›