88 citations · 171 across the 39 of their papers we have counts for
42 papers
Linear Bandits under Exact Sliding-Window Constraints
Seyed Mohammad Hadi Hosseini, Yasin Abbasi-Yadkori, Sattar Vakili
We study linear bandits under exact sliding-window constraints, where every consecutive block of actions must belong to a prescribed feasible set. In the offline setting, where the…
Instance-Dependent Regret for CMDPs with Step-Wise Constraints
Qian Zuo, Francesco Emanuele Stradi, Leyang Xue +1
We study online learning in episodic tabular constrained Markov decision processes with step-wise safety constraints. In such a setting, the constraints induce a safe subgraph that…
Wireless Physical-Layer Foundation Models: Architectures, Learning Paradigms, Applications, and Deployment
Mohammad Cheraghinia, Davide Buffelli, Liu Li +6
Foundation models, i.e., large neural networks pretrained on broad unlabeled data and adapted to many downstream tasks, have reshaped natural language processing and computer visio…
Learning Kernel-Based MDPs from Episodic Preferential Feedback
Nikola Pavlovic, Sattar Vakili, Qing Zhao
Human feedback often arrives as preferences rather than calibrated numeric rewards, motivating reinforcement learning from preferential feedback, also referred to as reinforcement…
Reinforcement Learning Using known Invariances
Alexandru Cioba, Aya Kayal, Laura Toni +2
In many real-world reinforcement learning (RL) problems, the environment exhibits inherent symmetries that can be exploited to improve learning efficiency. This paper develops a th…
No-Regret Thompson Sampling for Finite-Horizon Markov Decision Processes with Gaussian Processes
Jasmine Bayrooti, Sattar Vakili, Amanda Prorok +1
Thompson sampling (TS) is a powerful and widely used strategy for sequential decision-making, with applications ranging from Bayesian optimization to reinforcement learning (RL). D…
Bayesian Optimization from Human Feedback: Near-Optimal Regret Bounds
Aya Kayal, Sattar Vakili, Laura Toni +2
Bayesian optimization (BO) with preference-based feedback has recently garnered significant attention due to its emerging applications. We refer to this problem as Bayesian Optimiz…
Towards a Foundation Model for Communication Systems
Davide Buffelli, Sowmen Das, Yu-Wei Lin +5
Artificial Intelligence (AI) has demonstrated unprecedented performance across various domains, and its application to communication systems is an active area of research. While cu…
Group Think: Multiple Concurrent Reasoning Agents Collaborating at Token Level Granularity
Chan-Jan Hsu, Davide Buffelli, Jamie McGowan +4
Recent advances in large language models (LLMs) have demonstrated the power of reasoning through self-generated chains of thought. Multiple reasoning agents can collaborate to rais…
Near-Optimal Sample Complexity in Reward-Free Kernel-Based Reinforcement Learning
Aya Kayal, Sattar Vakili, Laura Toni +1
Reinforcement Learning (RL) problems are being considered under increasingly more complex structures. While tabular and linear models have been thoroughly explored, the analytical…
Kernel-Based Function Approximation for Average Reward Reinforcement Learning: An Optimist No-Regret Algorithm
Sattar Vakili, Julia Olkhovskaya
Reinforcement learning utilizing kernel ridge regression to predict the expected value function represents a powerful method with great representational capacity. This setting is a…
Open Problem: Order Optimal Regret Bounds for Kernel-Based Reinforcement Learning
Sattar Vakili
Reinforcement Learning (RL) has shown great empirical success in various application domains. The theoretical aspects of the problem have been extensively studied over past decades…
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…
Collaborative Learning in Kernel-based Bandits for Distributed Users
Sudeep Salgia, Sattar Vakili, Qing Zhao
We study collaborative learning among distributed clients facilitated by a central server. Each client is interested in maximizing a personalized objective function that is a weigh…
Near-Optimal Collaborative Learning in Bandits
Clémence Réda, Sattar Vakili, Emilie Kaufmann
This paper introduces a general multi-agent bandit model in which each agent is facing a finite set of arms and may communicate with other agents through a central controller in or…