Zobrazeno 1 - 10
of 2 844
pro vyhledávání: '"ERVEN, A"'
We consider a repeatedly played generalized Nash equilibrium game. This induces a multi-agent online learning problem with joint constraints. An important challenge in this setting is that the feasible set for each agent depends on the simultaneous m
Externí odkaz:
http://arxiv.org/abs/2410.02400
Autor:
Jöhlinger, Friederike, Semenenko, Henry, Sibson, Philip, Aktas, Djeylan, Rarity, John, Erven, Chris, Joshi, Siddarth, Faruque, Imad
The security proofs of the Quantum Key Distribution (QKD) protocols make certain assumptions about the operations of physical systems. Thus, appropriate modelling of devices to ensure that their operations are consistent with the models assumed in th
Externí odkaz:
http://arxiv.org/abs/2408.16835
Algorithm- and data-dependent generalization bounds are required to explain the generalization behavior of modern machine learning algorithms. In this context, there exists information theoretic generalization bounds that involve (various forms of) m
Externí odkaz:
http://arxiv.org/abs/2307.02501
Algorithmic recourse provides explanations that help users overturn an unfavorable decision by a machine learning system. But so far very little attention has been paid to whether providing recourse is beneficial or not. We introduce an abstract lear
Externí odkaz:
http://arxiv.org/abs/2306.00497
We consider the adversarial linear contextual bandit setting, which allows for the loss functions associated with each of $K$ arms to change over time without restriction. Assuming the $d$-dimensional contexts are drawn from a fixed known distributio
Externí odkaz:
http://arxiv.org/abs/2305.00832
In the first-order query model for zero-sum $K\times K$ matrix games, players observe the expected pay-offs for all their possible actions under the randomized action played by their opponent. This classical model has received renewed interest after
Externí odkaz:
http://arxiv.org/abs/2304.12768
Stochastic and adversarial data are two widely studied settings in online learning. But many optimization tasks are neither i.i.d. nor fully adversarial, which makes it of fundamental interest to get a better theoretical understanding of the world be
Externí odkaz:
http://arxiv.org/abs/2303.03272
Publikováno v:
NeurIPS 2023
We consider online prediction of a binary sequence with expert advice. For this setting, we devise label-efficient forecasting algorithms, which use a selective sampling scheme that enables collecting much fewer labels than standard procedures, while
Externí odkaz:
http://arxiv.org/abs/2302.08397
Autor:
Neuteboom, Thom, van Erven, Tim
We provide a new method for online learning, specifically prediction with expert advice, in a changing environment. In a non-changing environment the Squint algorithm has been designed to always function at least as well as other known algorithms and
Externí odkaz:
http://arxiv.org/abs/2209.06826
Different users of machine learning methods require different explanations, depending on their goals. To make machine learning accountable to society, one important goal is to get actionable options for recourse, which allow an affected user to chang
Externí odkaz:
http://arxiv.org/abs/2205.15834