中文
相关论文

相关论文: The price of bandit information in multiclass onli…

200 篇论文

Consider the domain of multiclass classification within the adversarial online setting. What is the price of relying on bandit feedback as opposed to full information? To what extent can an adaptive adversary amplify the loss compared to an…

机器学习 · 计算机科学 2024-02-13 Yuval Filmus , Steve Hanneke , Idan Mehalel , Shay Moran

We revisit the classical problem of multiclass classification with bandit feedback (Kakade, Shalev-Shwartz and Tewari, 2008), where each input classifies to one of $K$ possible labels and feedback is restricted to whether the predicted…

机器学习 · 计算机科学 2024-06-21 Liad Erez , Alon Cohen , Tomer Koren , Yishay Mansour , Shay Moran

The standard model and the bandit model are two generalizations of the mistake-bound model to online multiclass classification. In both models the learner guesses a classification in each round, but in the standard model the learner…

离散数学 · 计算机科学 2021-02-02 Jesse Geneson

We study the task of online learning in the presence of Massart noise. Instead of assuming that the online adversary chooses an arbitrary sequence of labels, we assume that the context $\mathbf{x}$ is selected adversarially but the label…

机器学习 · 计算机科学 2024-05-22 Ilias Diakonikolas , Vasilis Kontonis , Christos Tzamos , Nikos Zarifis

We present online boosting algorithms for multiclass classification with bandit feedback, where the learner only receives feedback about the correctness of its prediction. We propose an unbiased estimate of the loss using a randomized…

机器学习 · 统计学 2019-02-26 Daniel T. Zhang , Young Hun Jung , Ambuj Tewari

We study the problem of efficient online multiclass linear classification with bandit feedback, where all examples belong to one of $K$ classes and lie in the $d$-dimensional Euclidean space. Previous works have left open the challenge of…

We study multiclass PAC learning with bandit feedback, where inputs are classified into one of $K$ possible labels and feedback is limited to whether or not the predicted labels are correct. Our main contribution is in designing a novel…

机器学习 · 计算机科学 2024-06-19 Liad Erez , Alon Cohen , Tomer Koren , Yishay Mansour , Shay Moran

This paper addresses the problem of multiclass classification with corrupted or noisy bandit feedback. In this setting, the learner may not receive true feedback. Instead, it receives feedback that has been flipped with some non-zero…

机器学习 · 计算机科学 2021-06-08 Mudit Agarwal , Naresh Manwani

We present an efficient second-order algorithm with $\tilde{O}(\frac{1}{\eta}\sqrt{T})$ regret for the bandit online multiclass problem. The regret bound holds simultaneously with respect to a family of loss functions parameterized by…

机器学习 · 计算机科学 2018-01-19 Alina Beygelzimer , Francesco Orabona , Chicheng Zhang

We propose a new variant of online learning that we call "ambiguous online learning". In this setting, the learner is allowed to produce multiple predicted labels. Such an "ambiguous prediction" is considered correct when at least one of…

机器学习 · 计算机科学 2026-01-13 Vanessa Kosoy

We study online multiclass classification under bandit feedback. We extend the results of Daniely and Helbertal [2013] by showing that the finiteness of the Bandit Littlestone dimension is necessary and sufficient for bandit online…

机器学习 · 计算机科学 2024-01-23 Ananth Raman , Vinod Raman , Unique Subedi , Idan Mehalel , Ambuj Tewari

This paper introduces a new online learning framework for multiclass classification called learning with diluted bandit feedback. At every time step, the algorithm predicts a candidate label set instead of a single label for the observed…

机器学习 · 计算机科学 2021-05-19 Gaurav Batra , Naresh Manwani

We study the sample complexity of multiclass prediction in several learning settings. For the PAC setting our analysis reveals a surprising phenomenon: In sharp contrast to binary classification, we show that there exist multiclass…

机器学习 · 计算机科学 2016-04-19 Amit Daniely , Sivan Sabato , Shai Ben-David , Shai Shalev-Shwartz

We study the attainable regret for online linear optimization problems with bandit feedback, where unlike the full-information setting, the player can only observe its own loss rather than the full loss vector. We show that the price of…

机器学习 · 计算机科学 2014-08-12 Ohad Shamir

We consider the online multiclass linear classification under the bandit feedback setting. Beygelzimer, P\'{a}l, Sz\"{o}r\'{e}nyi, Thiruvenkatachari, Wei, and Zhang [ICML'19] considered two notions of linear separability, weak and strong…

机器学习 · 计算机科学 2021-09-01 Jittat Fakcharoenphol , Chayutpong Prompak

Multifidelity approximation is an important technique in scientific computation and simulation. In this paper, we introduce a bandit-learning approach for leveraging data of varying fidelities to achieve precise estimates of the parameters…

数值分析 · 数学 2022-02-22 Yiming Xu , Vahid Keshavarzzadeh , Robert M. Kirby , Akil Narayan

We study how to adapt to smoothly-varying ('easy') environments in well-known online learning problems where acquiring information is expensive. For the problem of label efficient prediction, which is a budgeted version of prediction with…

机器学习 · 计算机科学 2019-12-09 Siddharth Mitra , Aditya Gopalan

We consider the problem of online classification under a privacy constraint. In this setting a learner observes sequentially a stream of labelled examples $(x_t, y_t)$, for $1 \leq t \leq T$, and returns at each iteration $t$ a hypothesis…

机器学习 · 计算机科学 2021-06-28 Noah Golowich , Roi Livni

We develop a new approach to obtaining high probability regret bounds for online learning with bandit feedback against an adaptive adversary. While existing approaches all require carefully constructing optimistic and biased loss…

机器学习 · 计算机科学 2020-11-02 Chung-Wei Lee , Haipeng Luo , Chen-Yu Wei , Mengxiao Zhang

It is a remarkable fact that the same $O(\sqrt{T})$ regret rate can be achieved in both the Experts Problem and the Adversarial Multi-Armed Bandit problem albeit with a worse dependence on number of actions in the latter case. In contrast,…

机器学习 · 计算机科学 2022-10-05 Gautam Chandrasekaran , Ambuj Tewari
‹ 上一页 1 2 3 10 下一页 ›