88 citations · 171 across the 39 of their papers we have counts for
10 papers · 1 filter
Optimal Regret Bounds for Collaborative Learning in Bandits
Amitis Shidani, Sattar Vakili
We consider regret minimization in a general collaborative multi-agent multi-armed bandit model, in which each agent faces a finite set of arms and may communicate with other agent…
Robust Best-arm Identification in Linear Bandits
Wei Wang, Sattar Vakili, Ilija Bogunovic
We study the robust best-arm identification problem (RBAI) in the case of linear rewards. The primary objective is to identify a near-optimal robust arm, which involves selecting a…
Adversarial Contextual Bandits Go Kernelized
Gergely Neu, Julia Olkhovskaya, Sattar Vakili
We study a generalization of the problem of online learning in adversarial linear contextual bandits by incorporating loss functions that belong to a reproducing kernel Hilbert spa…
Random Exploration in Bayesian Optimization: Order-Optimal Regret and Computational Efficiency
Sudeep Salgia, Sattar Vakili, Qing Zhao
We consider Bayesian optimization using Gaussian Process models, also referred to as kernel-based bandit optimization. We study the methodology of exploring the domain using random…
Generative Diffusion Models for Radio Wireless Channel Modelling and Sampling
Ushnish Sengupta, Chinkuo Jao, Alberto Bernacchia +2
Channel modelling is essential to designing modern wireless communication systems. The increasing complexity of channel modelling and the cost of collecting high-quality wireless c…
Kernelized Reinforcement Learning with Order Optimal Regret Bounds
Sattar Vakili, Julia Olkhovskaya
Reinforcement learning (RL) has shown empirical success in various real world settings with complex models and large state-action spaces. The existing analytical results, however,…
Image generation with shortest path diffusion
Ayan Das, Stathi Fotiadis, Anil Batra +5
The field of image generation has made significant progress thanks to the introduction of Diffusion Models, which learn to progressively reverse a given image corruption. Recently,…
Trieste: Efficiently Exploring The Depths of Black-box Functions with TensorFlow
Victor Picheny, Joel Berkeley, Henry B. Moss +13
We present Trieste, an open-source Python package for Bayesian optimization and active learning benefiting from the scalability and efficiency of TensorFlow. Our library enables th…
Sample Complexity of Kernel-Based Q-Learning
Sing-Yuan Yeh, Fu-Chieh Chang, Chang-Wei Yueh +3
Modern reinforcement learning (RL) often faces an enormous state-action space. Existing analytical results are typically for settings with a small number of state-actions, or simpl…
Delayed Feedback in Kernel Bandits
Sattar Vakili, Danyal Ahmed, Alberto Bernacchia +1
Black box optimisation of an unknown function from expensive and noisy evaluations is a ubiquitous problem in machine learning, academic research and industrial production. An abst…