English
Related papers

Related papers: Online PAC-Bayes Learning

200 papers

Recent studies have empirically investigated different methods to train stochastic neural networks on a classification task by optimising a PAC-Bayesian bound via stochastic gradient descent. Most of these procedures need to replace the…

Machine Learning · Computer Science 2022-07-01 Eugenio Clerico , George Deligiannidis , Arnaud Doucet

We study the sequential general online regression, known also as the sequential probability assignments, under logarithmic loss when compared against a broad class of experts. We focus on obtaining tight, often matching, lower and upper…

Machine Learning · Computer Science 2023-02-02 Changlong Wu , Mohsen Heidari , Ananth Grama , Wojciech Szpankowski

We consider a PAC-Bayes type learning rule for binary classification, balancing the training error of a randomized ''posterior'' predictor with its KL divergence to a pre-specified ''prior''. This can be seen as an extension of a modified…

Machine Learning · Statistics 2026-03-25 Xiaohan Zhu , Mesrob I. Ohannessian , Nathan Srebro

We consider the problems of robust PAC learning from distributed and streaming data, which may contain malicious errors and outliers, and analyze their fundamental complexity questions. In particular, we establish lower bounds on the…

Machine Learning · Computer Science 2017-03-31 Jiashi Feng

Transfer learning seeks to accelerate sequential decision-making by leveraging offline data from related agents. However, data from heterogeneous sources that differ in observed features, distributions, or unobserved confounders often…

Machine Learning · Computer Science 2025-07-10 Xueping Gong , Wei You , Jiheng Zhang

In this paper, we generalize the problem of single-index model to the context of continual learning in which a learner is challenged with a sequence of tasks one by one and the dataset of each task is revealed in an online fashion. We…

Machine Learning · Statistics 2022-08-26 The Tien Mai

This work introduces the first small-loss and gradual-variation regret bounds for online portfolio selection, marking the first instances of data-dependent bounds for online convex optimization with non-Lipschitz, non-smooth losses. The…

Machine Learning · Computer Science 2023-11-07 Chung-En Tsai , Ying-Ting Lin , Yen-Huan Li

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

PAC-Bayes learning is an established framework to both assess the generalisation ability of learning algorithms, and design new learning algorithm by exploiting generalisation bounds as training objectives. Most of the exisiting bounds…

Machine Learning · Statistics 2023-05-31 Maxime Haddouche , Benjamin Guedj

We study the problem of online learning with dynamics, where a learner interacts with a stateful environment over multiple rounds. In each round of the interaction, the learner selects a policy to deploy and incurs a cost that depends on…

Machine Learning · Computer Science 2020-12-04 Kush Bhatia , Karthik Sridharan

Recently, there has been a significant focus on exploring the theoretical aspects of deep learning, especially regarding its performance in classification tasks. Bayesian deep learning has emerged as a unified probabilistic framework,…

Statistics Theory · Mathematics 2025-01-24 The Tien Mai

We consider a family of learning strategies for online optimization problems that evolve in continuous time and we show that they lead to no regret. From a more traditional, discrete-time viewpoint, this continuous-time approach allows us…

Optimization and Control · Mathematics 2014-02-28 Joon Kwon , Panayotis Mertikopoulos

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 predictive control of an unknown linear dynamical system with time varying cost functions which are unknown apriori. Specifically, we study the online learning problem where the control algorithm…

Machine Learning · Computer Science 2022-11-01 Deepan Muthirayan , Jianjun Yuan , Dileep Kalathil , Pramod P. Khargonekar

Current PAC-Bayes generalisation bounds are restricted to scalar metrics of performance, such as the loss or error rate. However, one ideally wants more information-rich certificates that control the entire distribution of possible…

Machine Learning · Statistics 2024-12-10 Reuben Adams , John Shawe-Taylor , Benjamin Guedj

This paper presents a PAC-Bayes framework for learning controllers for unknown stochastic linear discrete-time systems, where the system parameters are drawn from a fixed but unknown distribution. We derive a data-dependent high probability…

Optimization and Control · Mathematics 2026-05-22 Yujia Luo , Ye Pu , Jonathan H. Manton , Jingge Zhu

We consider online optimization with binary decision variables and convex loss functions. We design a new algorithm, binary online gradient descent (bOGD) and bound its expected dynamic regret. We provide a regret bound that holds for any…

Optimization and Control · Mathematics 2022-01-21 Antoine Lesage-Landry , Joshua A. Taylor , Duncan S. Callaway

Bayesian persuasion studies how an informed sender should partially disclose information to influence the behavior of a self-interested receiver. Classical models make the stringent assumption that the sender knows the receiver's utility.…

Computer Science and Game Theory · Computer Science 2021-06-14 Matteo Castiglioni , Alberto Marchesi , Andrea Celli , Nicola Gatti

Some machine learning applications require continual learning - where data comes in a sequence of datasets, each is used for training and then permanently discarded. From a Bayesian perspective, continual learning seems straightforward:…

Machine Learning · Statistics 2019-02-19 Sebastian Farquhar , Yarin Gal

We present a new analysis of the problem of learning with drifting distributions in the batch setting using the notion of discrepancy. We prove learning bounds based on the Rademacher complexity of the hypothesis set and the discrepancy of…

Machine Learning · Computer Science 2012-08-28 Mehryar Mohri , Andres Munoz Medina