SV
Sattar Vakili
cs.LGstat.MLcs.AImath.OCcs.CVeess.SPmath.STstat.THcs.CEcs.IT
On Valency
published · living versionsW_mz6xkusc·v1 · currentpublished
Preprints & journals
46 papers in the corpus · 2011–2026Linear Bandits under Exact Sliding-Window Constraints2610.08745v1 · Seyed Mohammad Hadi Hosseini, Yasin Abbasi-Yadkori, Sattar Vakili2026 · 0 citationsarXiv
Instance-Dependent Regret for CMDPs with Step-Wise Constraints2610.02520v1 · Qian Zuo, Francesco Emanuele Stradi, Leyang Xue et al.2026 · 0 citationsarXiv
Wireless Physical-Layer Foundation Models: Architectures, Learning Paradigms, Applications, and Deployment2608.20486v1 · Mohammad Cheraghinia, Davide Buffelli, Liu Li et al.2026 · 0 citationsarXiv
Learning Kernel-Based MDPs from Episodic Preferential Feedback2605.23650v2 · Nikola Pavlovic, Sattar Vakili, Qing Zhao2026 · 0 citationsarXiv
Many Needles in a Haystack: Active Hit Discovery for Perturbation Experiments2605.10196v1 · Andrea Rubbi, Arpit Merchant, Samuel Ogden et al.2026 · 1 citationarXiv
A Finite Time Analysis of Thompson Sampling for Bayesian Optimization with Preferential Feedback2604.25025v1 · Joseph Lazzaro, Davide Buffelli, Da-shan Shiu et al.2026 · 0 citationsarXiv
Shortest-Path Flow Matching with Mixture-Conditioned Bases for OOD Generalization to Unseen Conditions2601.11827v2 · Andrea Rubbi, Amir Akbarnejad, Mohammad Vali Sanian et al.2026 · 0 citationsarXiv
Reinforcement Learning Using known Invariances2511.03473v2 · Alexandru Cioba, Aya Kayal, Laura Toni et al.2025 · 0 citationsarXiv
No-Regret Thompson Sampling for Finite-Horizon Markov Decision Processes with Gaussian Processes2510.20725v1 · Jasmine Bayrooti, Sattar Vakili, Amanda Prorok et al.2025 · 0 citationsarXiv
Bayesian Optimization from Human Feedback: Near-Optimal Regret Bounds2505.23673v1 · Aya Kayal, Sattar Vakili, Laura Toni et al.2025 · 0 citationsarXiv
Towards a Foundation Model for Communication Systems2505.14603v1 · Davide Buffelli, Sowmen Das, Yu-Wei Lin et al.2025 · 0 citationsarXiv
Group Think: Multiple Concurrent Reasoning Agents Collaborating at Token Level Granularity2505.11107v1 · Chan-Jan Hsu, Davide Buffelli, Jamie McGowan et al.2025 · 0 citationsarXiv
Near-Optimal Sample Complexity in Reward-Free Kernel-Based Reinforcement Learning2502.07715v2 · Aya Kayal, Sattar Vakili, Laura Toni et al.2025 · 0 citationsarXiv
Kernel-Based Function Approximation for Average Reward Reinforcement Learning: An Optimist No-Regret Algorithm2410.23498v1 · Sattar Vakili, Julia Olkhovskaya2024 · 0 citationsarXiv
Open Problem: Order Optimal Regret Bounds for Kernel-Based Reinforcement Learning2406.15250v1 · Sattar Vakili2024 · 0 citationsarXiv
Optimal Regret Bounds for Collaborative Learning in Bandits2312.09674v1 · Amitis Shidani, Sattar Vakili2023 · 0 citationsarXiv
Robust Best-arm Identification in Linear Bandits2311.04731v1 · Wei Wang, Sattar Vakili, Ilija Bogunovic2023 · 0 citationsarXiv
Random Exploration in Bayesian Optimization: Order-Optimal Regret and Computational Efficiency2310.15351v2 · Sudeep Salgia, Sattar Vakili, Qing Zhao2023 · 0 citationsarXiv
Adversarial Contextual Bandits Go Kernelized2310.01609v1 · Gergely Neu, Julia Olkhovskaya, Sattar Vakili2023 · 0 citationsarXiv
Generative Diffusion Models for Radio Wireless Channel Modelling and Sampling2308.05583v1 · Ushnish Sengupta, Chinkuo Jao, Alberto Bernacchia et al.2023 · 32 citationsarXiv
Kernelized Reinforcement Learning with Order Optimal Regret Bounds2306.07745v3 · Sattar Vakili, Julia Olkhovskaya2023 · 2 citationsarXiv
Image generation with shortest path diffusion2306.00501v1 · Ayan Das, Stathi Fotiadis, Anil Batra et al.2023 · 0 citationsarXiv
Trieste: Efficiently Exploring The Depths of Black-box Functions with TensorFlow2302.08436v1 · Victor Picheny, Joel Berkeley, Henry B. Moss et al.2023 · 23 citationsarXiv
Delayed Feedback in Kernel Bandits2302.00392v1 · Sattar Vakili, Danyal Ahmed, Alberto Bernacchia et al.2023 · 0 citationsarXiv
Sample Complexity of Kernel-Based Q-Learning2302.00727v1 · Sing-Yuan Yeh, Fu-Chieh Chang, Chang-Wei Yueh et al.2023 · 0 citationsarXiv
Collaborative Learning in Kernel-based Bandits for Distributed Users2207.07948v2 · Sudeep Salgia, Sattar Vakili, Qing Zhao2022 · 4 citationsarXiv
Provably and Practically Efficient Neural Contextual Bandits2206.00099v1 · Sudeep Salgia, Sattar Vakili, Qing Zhao2022 · 2 citationsarXiv
Near-Optimal Collaborative Learning in Bandits2206.00121v2 · Cl'emence R'eda, Sattar Vakili, Emilie Kaufmann2022 · 4 citationsarXiv
Improved Convergence Rates for Sparse Approximation Methods in Kernel-Based Learning2202.04005v2 · Sattar Vakili, Jonathan Scarlett, Da-shan Shiu et al.2022 · 4 citationsarXiv
Open Problem: Tight Online Confidence Intervals for RKHS Elements2110.15458v1 · Sattar Vakili, Jonathan Scarlett, Tara Javidi2021 · 3 citationsarXiv
Uniform Generalization Bounds for Overparameterized Neural Networks2109.06099v3 · Sattar Vakili, Michael Bromberg, Jezabel Garcia et al.2021 · 0 citationsarXiv
Optimal Order Simple Regret for Gaussian Process Bandits2108.09262v1 · Sattar Vakili, Nacime Bouziani, Sepehr Jalali et al.2021 · 14 citationsarXiv
A Domain-Shrinking based Bayesian Optimization Algorithm with Order-Optimal Regret Performance2010.13997v3 · Sudeep Salgia, Sattar Vakili, Qing Zhao2020 · 7 citationsarXiv
On Information Gain and Regret Bounds in Gaussian Process Bandits2009.06966v3 · Sattar Vakili, Kia Khezeli, Victor Picheny2020 · 19 citationsarXiv
Scalable Thompson Sampling using Sparse Gaussian Process Models2006.05356v4 · Sattar Vakili, Henry Moss, Artem Artemev et al.2020 · 8 citationsarXiv
Stochastic Coordinate Minimization with Progressive Precision for Stochastic Convex Optimization2003.05482v1 · Sudeep Salgia, Qing Zhao, Sattar Vakili2020 · 0 citationsarXiv
Amortized variance reduction for doubly stochastic objectives2003.04125v1 · Ayman Boustati, Sattar Vakili, James Hensman et al.2020 · 0 citationsarXiv
Regret Bounds for Noise-Free Kernel-Based Bandits2002.05096v2 · Sattar Vakili2020 · 0 citationsarXiv
Ordinal Bayesian Optimisation1912.02493v1 · Victor Picheny, Sattar Vakili, Artem Artemev2019 · 5 citationsarXiv
Adaptive Sensor Placement for Continuous Spaces1905.06821v1 · James A Grant, Alexis Boukouvalas, Ryan-Rhys Griffiths et al.2019 · 12 citationsarXiv
Stochastic Gradient Descent on a Tree: an Adaptive and Robust Approach to Stochastic Convex Optimization1901.05947v3 · Sattar Vakili, Sudeep Salgia, Qing Zhao2019 · 6 citationsarXiv
Decision Variance in Online Learning1807.09089v2 · Sattar Vakili, Alexis Boukouvalas, Qing Zhao2018 · 2 citationsarXiv
Multi-Armed Bandits on Partially Revealed Unit Interval Graphs1802.04339v3 · Xiao Xu, Sattar Vakili, Qing Zhao et al.2018 · 4 citationsarXiv
Anomaly Detection in Hierarchical Data Streams under Unknown Models1709.03573v1 · Sattar Vakili, Qing Zhao, Chang Liu et al.2017 · 1 citationarXiv
Risk-Averse Multi-Armed Bandit Problems under Mean-Variance Measure1604.05257v3 · Sattar Vakili, Qing Zhao2016 · 86 citationsarXivon Valency
Deterministic Sequencing of Exploration and Exploitation for Multi-Armed Bandit Problems1106.6104v3 · Sattar Vakili, Keqin Liu, Qing Zhao2011 · 90 citationsarXiv
Career total: 66 works. 46 are in this corpus.
Profile built from the corpus for this byline.
Author records are still filling in while the Hub is in alpha. If this is your page, you'll be able to claim it soon. Spot a mistake? Tell us.