English
Related papers

Related papers: Apple Tasting: Combinatorial Dimensions and Minima…

200 papers

We characterize the minimax rate of estimating the second-order calibration error for binary classification, which quantifies whether a higher-order predictor's epistemic-uncertainty estimate matches the conditional variance of the label…

Machine Learning · Computer Science 2026-05-11 Kamil Ciosek , Banafsheh Rafiee , Sina Ghiassian , Nicolò Felicioni

Most learning algorithms with formal regret guarantees assume that all mistakes are recoverable and essentially rely on trying all possible behaviors. This approach is problematic when some mistakes are "catastrophic", i.e., irreparable. We…

Machine Learning · Computer Science 2025-08-07 Benjamin Plaut , Hanlin Zhu , Stuart Russell

Uncertainty quantification is crucial in safety-critical systems, where decisions must be made under uncertainty. In particular, we consider the problem of online uncertainty quantification, where data points arrive sequentially. Online…

Machine Learning · Computer Science 2026-04-21 Junyoung Yang , Kyungmin Kim , Sangdon Park

We introduce a novel online multitask setting. In this setting each task is partitioned into a sequence of segments that is unknown to the learner. Associated with each segment is a hypothesis from some hypothesis class. We give algorithms…

Machine Learning · Computer Science 2020-08-18 Mark Herbster , Stephen Pasteris , Lisa Tse

We provide a full characterization of the concept classes that are optimistically universally online learnable with $\{0, 1\}$ labels. The notion of optimistically universal online learning was defined in [Hanneke, 2021] in order to…

Machine Learning · Statistics 2025-01-16 Steve Hanneke , Hongao Wang

In this paper, we study a special bandit setting of online stochastic linear optimization, where only one-bit of information is revealed to the learner at each round. This problem has found many applications including online advertisement…

Machine Learning · Computer Science 2015-09-28 Lijun Zhang , Tianbao Yang , Rong Jin , Zhi-Hua Zhou

The selection of the assumed effect size (AES) critically determines the duration of an experiment, and hence its accuracy and efficiency. Traditionally, experimenters determine AES based on domain knowledge. However, this method becomes…

Machine Learning · Computer Science 2025-04-15 Yu Liu , Runzhe Wan , James McQueen , Doug Hains , Jinxiang Gu , Rui Song

Calibrated predictions are useful because their numerical values can be interpreted as probabilities. Calibration errors are therefore widely used to evaluate, compare, and tune probabilistic predictors. Recently, Haghtalab et al. (2024)…

Machine Learning · Computer Science 2026-05-19 Yuxuan Lu , Yifan Wu , Jason Hartline , Lunjia Hu

We propose a general framework for studying adaptive regret bounds in the online learning framework, including model selection bounds and data-dependent bounds. Given a data- or model-dependent bound we ask, "Does there exist some algorithm…

Machine Learning · Computer Science 2020-02-14 Dylan J. Foster , Alexander Rakhlin , Karthik Sridharan

Most classifiers operate by selecting the maximum of an estimate of the conditional distribution $p(y|x)$ where $x$ stands for the features of the instance to be classified and $y$ denotes its label. This often results in a {\em hubristic…

Machine Learning · Statistics 2019-03-01 Yotam Hechtlinger , Barnabás Póczos , Larry Wasserman

Blasiok et al. [2023] proposed distance to calibration as a natural measure of calibration error that unlike expected calibration error (ECE) is continuous. Recently, Qiao and Zheng [2024] gave a non-constructive argument establishing the…

Machine Learning · Computer Science 2024-10-08 Eshwar Ram Arunachaleswaran , Natalie Collina , Aaron Roth , Mirah Shi

We study the problem of agnostic PAC reinforcement learning (RL): given a policy class $\Pi$, how many rounds of interaction with an unknown MDP (with a potentially large state and action space) are required to learn an…

Machine Learning · Computer Science 2023-10-11 Zeyu Jia , Gene Li , Alexander Rakhlin , Ayush Sekhari , Nathan Srebro

In this paper, we introduce directional feedback in the ordinal regression setting, in which the learner receives feedback on whether the predicted label is on the left or the right side of the actual label. This is a weak supervision…

Machine Learning · Computer Science 2025-12-23 Naresh Manwani , M Elamparithy , Tanish Taneja

We show that top-down decision tree learning heuristics are amenable to highly efficient learnability estimation: for monotone target functions, the error of the decision tree hypothesis constructed by these heuristics can be estimated with…

Machine Learning · Computer Science 2020-11-04 Guy Blanc , Neha Gupta , Jane Lange , Li-Yang Tan

We consider the problem of adversarial (non-stochastic) online learning with partial information feedback, where at each round, a decision maker selects an action from a finite set of alternatives. We develop a black-box approach for such…

Machine Learning · Computer Science 2021-07-28 Thodoris Lykouris , Karthik Sridharan , Eva Tardos

Online decision systems routinely operate under delayed feedback and order-sensitive (noncommutative) dynamics: actions affect which observations arrive, and in what sequence. Taking a Bregman divergence $D_\Phi$ as the loss benchmark, we…

Machine Learning · Computer Science 2025-11-18 Duo Yi

Many engineered systems must balance competing objectives, such as performance and safety, cost and reliability, or efficiency and sustainability, and are naturally modeled as compositions of interacting subsystems. We study online…

Optimization and Control · Mathematics 2026-04-27 Meshal Alharbi , Munther A. Dahleh , Gioele Zardini

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…

Machine Learning · Computer Science 2024-05-22 Ilias Diakonikolas , Vasilis Kontonis , Christos Tzamos , Nikos Zarifis

Personalized alignment aims to adapt large language models to heterogeneous user preferences, yet the precise theoretical conditions for its statistical efficiency have not been formally established. This paper characterizes the conditions…

Machine Learning · Computer Science 2026-05-12 Enoch Hyunwook Kang

We investigate contextual online learning with nonparametric (Lipschitz) comparison classes under different assumptions on losses and feedback information. For full information feedback and Lipschitz losses, we design the first explicit…

Machine Learning · Statistics 2017-07-03 Nicolò Cesa-Bianchi , Pierre Gaillard , Claudio Gentile , Sébastien Gerchinovitz