English
Related papers

Related papers: High-Probability Risk Bounds via Sequential Predic…

200 papers

Much of the work in online learning focuses on the study of sublinear upper bounds on the regret. In this work, we initiate the study of best-case lower bounds in online convex optimization, wherein we bound the largest improvement an…

Machine Learning · Computer Science 2021-06-25 Cristóbal Guzmán , Nishant A. Mehta , Ali Mortazavi

We study online learning in contextual pay-per-click auctions where at each of the $T$ rounds, the learner receives some context along with a set of ads and needs to make an estimate on their click-through rate (CTR) in order to run a…

Machine Learning · Computer Science 2023-10-10 Mengxiao Zhang , Haipeng Luo

Online prediction from experts is a fundamental problem in machine learning and several works have studied this problem under privacy constraints. We propose and analyze new algorithms for this problem that improve over the regret bounds of…

Machine Learning · Computer Science 2023-07-03 Hilal Asi , Vitaly Feldman , Tomer Koren , Kunal Talwar

This paper studies an online optimization problem with a finite prediction window of cost functions and additional switching costs on decisions. We propose two gradient-based online algorithms: Receding Horizon Gradient Descent (RHGD), and…

Optimization and Control · Mathematics 2020-03-10 Yingying Li , Guannan Qu , Na Li

We study Online Linear Programming (OLP) with batching. The planning horizon is cut into $K$ batches, and the decisions on customers arriving within a batch can be delayed to the end of their associated batch. Compared with OLP without…

Machine Learning · Computer Science 2024-08-02 Haoran Xu , Peter W. Glynn , Yinyu Ye

We develop a novel family of algorithms for the online learning setting with regret against any data sequence bounded by the empirical Rademacher complexity of that sequence. To develop a general theory of when this type of adaptive regret…

Machine Learning · Computer Science 2017-04-14 Dylan J. Foster , Alexander Rakhlin , Karthik Sridharan

Computationally efficient contextual bandits are often based on estimating a predictive model of rewards given contexts and arms using past data. However, when the reward model is not well-specified, the bandit algorithm may incur…

Machine Learning · Computer Science 2021-06-14 Sanath Kumar Krishnamurthy , Vitor Hadad , Susan Athey

Regret bounds in online learning compare the player's performance to $L^*$, the optimal performance in hindsight with a fixed strategy. Typically such bounds scale with the square root of the time horizon $T$. The more refined concept of…

Machine Learning · Computer Science 2018-02-12 Zeyuan Allen-Zhu , Sébastien Bubeck , Yuanzhi Li

Confidence intervals are a crucial building block in the analysis of various online learning problems. The analysis of kernel based bandit and reinforcement learning problems utilize confidence intervals applicable to the elements of a…

Machine Learning · Statistics 2021-11-01 Sattar Vakili , Jonathan Scarlett , Tara Javidi

Online learning has traditionally focused on the expected rewards. In this paper, a risk-averse online learning problem under the performance measure of the mean-variance of the rewards is studied. Both the bandit and full information…

Machine Learning · Statistics 2019-03-15 Sattar Vakili , Alexis Boukouvalas , Qing Zhao

We investigate the concept of algorithmic replicability introduced by Impagliazzo et al. 2022, Ghazi et al. 2021, Ahn et al. 2024 in an online setting. In our model, the input sequence received by the online learner is generated from…

Machine Learning · Computer Science 2024-11-22 Saba Ahmadi , Siddharth Bhandari , Avrim Blum

We study the problem of prediction with expert advice when the number of experts in question may be extremely large or even infinite. We devise an algorithm that obtains a tight regret bound of $\widetilde{O}(\epsilon T + N + \sqrt{NT})$,…

Machine Learning · Computer Science 2017-02-28 Alon Cohen , Shie Mannor

We investigate the problem of online learning, which has gained significant attention in recent years due to its applicability in a wide range of fields from machine learning to game theory. Specifically, we study the online optimization of…

Machine Learning · Computer Science 2021-09-29 Kaan Gokcesu , Hakan Gokcesu

In this paper, we prove that Distributional Reinforcement Learning (DistRL), which learns the return distribution, can obtain second-order bounds in both online and offline RL in general settings with function approximation. Second-order…

Machine Learning · Computer Science 2024-02-13 Kaiwen Wang , Owen Oertell , Alekh Agarwal , Nathan Kallus , Wen Sun

We study a class of adversarial bandit optimization problems in which the loss functions may be non-convex and non-smooth. In each round, the learner observes a loss that consists of an underlying linear component together with an…

Machine Learning · Computer Science 2026-03-30 Zhuoyu Cheng , Kohei Hatano , Eiji Takimoto

We introduce a new online convex optimization algorithm that adaptively chooses its regularization function based on the loss functions observed so far. This is in contrast to previous algorithms that use a fixed regularization function…

Machine Learning · Computer Science 2010-07-08 H. Brendan McMahan , Matthew Streeter

We study the problem of online learning in a class of Markov decision processes known as linearly solvable MDPs. In the stationary version of this problem, a learner interacts with its environment by directly controlling the state…

Machine Learning · Computer Science 2017-06-07 Gergely Neu , Vicenç Gómez

In online learning, the dynamic regret metric chooses the reference (optimal) solution that may change over time, while the typical (static) regret metric assumes the reference solution to be constant over the whole time horizon. The…

Machine Learning · Computer Science 2019-09-04 Yawei Zhao , Shuang Qiu , Ji Liu

The Adversarial Markov Decision Process (AMDP) is a learning framework that deals with unknown and varying tasks in decision-making applications like robotics and recommendation systems. A major limitation of the AMDP formalism, however, is…

Machine Learning · Statistics 2024-05-06 Sang Bin Moon , Abolfazl Hashemi

Probability estimates generated by boosting ensembles are poorly calibrated because of the margin maximization nature of the algorithm. The outputs of the ensemble need to be properly calibrated before they can be used as probability…

Machine Learning · Computer Science 2020-01-20 Nikolaos Nikolaou , Joseph Mellor , Nikunj C. Oza , Gavin Brown