English
Related papers

Related papers: PAC Learning with Bandit Feedback: Sharp Sample Co…

200 papers

In this paper, we introduce the notion of replicable policies in the context of stochastic bandits, one of the canonical problems in interactive learning. A policy in the bandit environment is called replicable if it pulls, with high…

Machine Learning · Computer Science 2023-02-16 Hossein Esfandiari , Alkis Kalavasis , Amin Karbasi , Andreas Krause , Vahab Mirrokni , Grigoris Velegkas

Generalizable depth completion enables the acquisition of dense metric depth maps for unseen environments, offering robust perception capabilities for various downstream tasks. However, training such models typically requires large-scale…

Computer Vision and Pattern Recognition · Computer Science 2025-07-11 Haotian Wang , Aoran Xiao , Xiaoqin Zhang , Meng Yang , Shijian Lu

We consider the problem of estimating how well a model class is capable of fitting a distribution of labeled data. We show that it is often possible to accurately estimate this "learnability" even when given an amount of data that is too…

Machine Learning · Computer Science 2019-03-26 Weihao Kong , Gregory Valiant

We study the contextual linear bandit problem, a version of the standard stochastic multi-armed bandit (MAB) problem where a learner sequentially selects actions to maximize a reward which depends also on a user provided per-round context.…

Machine Learning · Computer Science 2018-10-02 Roshan Shariff , Or Sheffet

Most modern unsupervised domain adaptation (UDA) approaches are rooted in domain alignment, i.e., learning to align source and target features to learn a target domain classifier using source labels. In semi-supervised domain adaptation…

Computer Vision and Pattern Recognition · Computer Science 2021-11-30 Samarth Mishra , Kate Saenko , Venkatesh Saligrama

We theoretically explore the relationship between sample-efficiency and adaptivity in reinforcement learning. An algorithm is sample-efficient if it uses a number of queries $n$ to the environment that is polynomial in the dimension $d$ of…

Machine Learning · Computer Science 2024-05-29 Emmeran Johnson , Ciara Pike-Burke , Patrick Rebeschini

To learn target discriminative representations, using pseudo-labels is a simple yet effective approach for unsupervised domain adaptation. However, the existence of false pseudo-labels, which may have a detrimental influence on learning…

Computer Vision and Pattern Recognition · Computer Science 2019-08-02 Jaehoon Choi , Minki Jeong , Taekyung Kim , Changick Kim

We consider the problem of probably approximately correct (PAC) ranking $n$ items by adaptively eliciting subset-wise preference feedback. At each round, the learner chooses a subset of $k$ items and observes stochastic feedback indicating…

Machine Learning · Computer Science 2019-03-06 Aadirupa Saha , Aditya Gopalan

We consider an online learning problem with one-sided feedback, in which the learner is able to observe the true label only for positively predicted instances. On each round, $k$ instances arrive and receive classification outcomes…

Machine Learning · Computer Science 2022-06-10 Yahav Bechavod , Aaron Roth

We revisit the problem of characterising the complexity of Quantum PAC learning, as introduced by Bshouty and Jackson [SIAM J. Comput. 1998, 28, 1136-1153]. Several quantum advantages have been demonstrated in this setting, however, none…

Quantum Physics · Physics 2023-09-21 Wilfred Salmon , Sergii Strelchuk , Tom Gur

Contextual bandits are a form of multi-armed bandit in which the agent has access to predictive side information (known as the context) for each arm at each time step, and have been used to model personalized news recommendation, ad…

Machine Learning · Statistics 2017-05-25 Aniket Anand Deshmukh , Urun Dogan , Clayton Scott

Valiant's 1984 paper is widely credited with introducing the PAC learning model, but it, in fact, introduced a different model: unlike PAC learning, the learner receives only positives, may issue membership queries, and must output a…

Machine Learning · Statistics 2026-05-14 Steve Hanneke , Anay Mehrotra , Grigoris Velegkas , Manolis Zampetakis

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…

Numerical Analysis · Mathematics 2022-02-22 Yiming Xu , Vahid Keshavarzzadeh , Robert M. Kirby , Akil Narayan

We study the problem of PAC learning $\gamma$-margin halfspaces with Random Classification Noise. We establish an information-computation tradeoff suggesting an inherent gap between the sample complexity of the problem and the sample…

Machine Learning · Computer Science 2023-06-29 Ilias Diakonikolas , Jelena Diakonikolas , Daniel M. Kane , Puqian Wang , Nikos Zarifis

In machine learning, the notion of multi-armed bandits refers to a class of online learning problems, in which an agent is supposed to simultaneously explore and exploit a given set of choice alternatives in the course of a sequential…

Machine Learning · Computer Science 2021-07-13 Viktor Bengs , Robert Busa-Fekete , Adil El Mesaoudi-Paul , Eyke Hüllermeier

Probably Approximately Correct (i.e., PAC) learning is a core concept of sample complexity theory, and efficient PAC learnability is often seen as a natural counterpart to the class P in classical computational complexity. But while the…

Computational Complexity · Computer Science 2023-04-28 Cornelius Brand , Robert Ganian , Kirill Simonov

Exploration policies in Bayesian bandits maximize the average reward over problem instances drawn from some distribution $\mathcal{P}$. In this work, we learn such policies for an unknown distribution $\mathcal{P}$ using samples from…

Machine Learning · Computer Science 2020-06-11 Craig Boutilier , Chih-Wei Hsu , Branislav Kveton , Martin Mladenov , Csaba Szepesvari , Manzil Zaheer

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…

Machine Learning · Statistics 2019-02-26 Daniel T. Zhang , Young Hun Jung , Ambuj Tewari

We consider the linear contextual multi-class multi-period packing problem (LMMP) where the goal is to pack items such that the total vector of consumption is below a given budget vector and the total value is as large as possible. We…

Machine Learning · Statistics 2023-06-02 Wonyoung Kim , Garud Iyengar , Assaf Zeevi

In-context learning is a surprising and important phenomenon that emerged when modern language models were scaled to billions of learned parameters. Without modifying a large language model's weights, it can be tuned to perform various…

Computation and Language · Computer Science 2023-03-15 Noam Wies , Yoav Levine , Amnon Shashua