151 citations · 185 across the 15 of their papers we have counts for
15 papers
Prior-Dependent Allocations for Bayesian Fixed-Budget Best-Arm Identification in Structured Bandits
Nicolas Nguyen, Imad Aouali, András György +1
We study the problem of Bayesian fixed-budget best-arm identification (BAI) in structured bandits. We propose an algorithm that uses fixed allocations based on the prior informatio…
Online RL in Linearly -Realizable MDPs Is as Easy as in Linear MDPs If You Learn What to Ignore
Gellért Weisz, András György, Csaba Szepesvári
We consider online reinforcement learning (RL) in episodic Markov decision processes (MDPs) under the linear -realizability assumption, where it is assumed that the action-val…
Perception, performance, and detectability of conversational artificial intelligence across 32 university courses
Hazem Ibrahim, Fengyuan Liu, Rohail Asim +36
The emergence of large language models has led to the development of powerful tools such as ChatGPT that can produce text indistinguishable from human-generated work. With the incr…
Optimistic Meta-Gradients
Sebastian Flennerhag, Tom Zahavy, Brendan O'Donoghue +3
We study the connection between gradient-based meta-learning and convex op-timisation. We observe that gradient descent with momentum is a special case of meta-gradients, and build…
Understanding Self-Predictive Learning for Reinforcement Learning
Yunhao Tang, Zhaohan Daniel Guo, Pierre Harvey Richemond +13
We study the learning dynamics of self-predictive learning for reinforcement learning, a family of algorithms that learn representations by minimizing the prediction error of their…
Generalization Bounds for Few-Shot Transfer Learning with Pretrained Classifiers
Tomer Galanti, András György, Marcus Hutter
We study the ability of foundation models to learn representations for classification that are transferable to new, unseen classes. Recent results in the literature show that repre…
Confident Approximate Policy Iteration for Efficient Local Planning in -realizable MDPs
Gellért Weisz, András György, Tadashi Kozuno +1
We consider approximate dynamic programming in -discounted Markov decision processes and apply it to approximate planning with linear value-function approximation. Our first con…
Distributed Contextual Linear Bandits with Minimax Optimal Communication Cost
Sanae Amani, Tor Lattimore, András György +1
We study distributed contextual linear bandits with stochastic contexts, where agents act cooperatively to solve a linear bandit-optimization problem with -dimensional featu…
Non-stationary Bandits and Meta-Learning with a Small Set of Optimal Arms
MohammadJavad Azizi, Thang Duong, Yasin Abbasi-Yadkori +3
We study a sequential decision problem where the learner faces a sequence of -armed bandit tasks. The task boundaries might be known (the bandit meta-learning setting), or unkno…
On the Role of Neural Collapse in Transfer Learning
Tomer Galanti, András György, Marcus Hutter
We study the ability of foundation models to learn representations for classification that are transferable to new, unseen classes. Recent results in the literature show that repre…
On Multi-objective Policy Optimization as a Tool for Reinforcement Learning: Case Studies in Offline RL and Finetuning
Abbas Abdolmaleki, Sandy H. Huang, Giulia Vezzani +11
Many advances that have improved the robustness and efficiency of deep reinforcement learning (RL) algorithms can, in one way or another, be understood as introducing additional ob…
Defending Against Image Corruptions Through Adversarial Augmentations
Dan A. Calian, Florian Stimberg, Olivia Wiles +4
Modern neural networks excel at image classification, yet they remain vulnerable to common image corruptions such as blur, speckle noise or fog. Recent methods that focus on this p…
Confident Off-Policy Evaluation and Selection through Self-Normalized Importance Weighting
Ilja Kuzborskij, Claire Vernade, András György +1
We consider off-policy evaluation in the contextual bandit setting for the purpose of obtaining a robust off-policy selection strategy, where the selection strategy is evaluated ba…
Non-Stationary Delayed Bandits with Intermediate Observations
Claire Vernade, Andras Gyorgy, Timothy Mann
Online recommender systems often face long delays in receiving feedback, especially when optimizing for some long-term metrics. While mitigating the effects of delays in learning i…
Efficient Tracking of Large Classes of Experts
András Gyorgy, Tamás Linder, Gábor Lugosi
In the framework of prediction of individual sequences, sequential prediction methods are to be constructed that perform nearly as well as the best expert from a given class. We co…