Research Interests

Reinforcement learning; bandits; Bayesian optimisation; Gaussian processes and kernel methods; sequential decision making; generative and diffusion models; transformers and foundation models; probabilistic modelling; information theory; applications to engineering, science, and experimental design.

Machine Learning, Bandit, Reinforcement learning, kernel methods, Google Scholar, LinkedIn, Cornell, MediaTek,

Latest

May 2025: Mapping and reprogramming human tissue microenvironments with MintFlow is under review at Nature.
June 2025: Reinforcement Learning with Thompson Sampling: No-Regret Performance over Finite Horizons is accepted to be presented at the ICML 2025 workshop Exploration in AI Today.
June 2025: Towards a Foundation Model for Communication Systems is accepted to be presented at the ICML 2025 workshop ML for wireless communication and networks.
May 2025: Bayesian Optimization from Human Feedback: Near-Optimal Regret Bounds is accepted at ICML 2025.
May 2025: Will be giving a tutorial on Foundation Models for Communication Systems at IEEE GLOBECOM, December 2025, Taipei.
March 2025: Giving a Tech Talk on AI and Communication at Cambridge University, Mar 10th.
Feburary 2025: Giving a presentation at the Computational Statistics and Machine Learning (OxCSML) seminar series, Oxford University, Feb 21st.
January 2025: Near-Optimal Sample Complexity in Reward-Free Reinforcement Learning is accepted at AISTATS 2025.
December 2024: Presenting our NeurIPS paper at local meetup, Cambrdige University, Dec 6th.
October 2024: Kernel-Based Function Approximation for Average Reward Reinforcement Learning: An Optimist No-Regret Algorithm is accepted at NeurIPS 2024.
October 2024: Trieste: Efficiently Exploring The Depths of Black-box Functions with TensorFlow is accepted at NeurIPS 2024 Workshop on Bayesian Decision-making and Uncertainty.
September 2024: Adversarial Contextual Bandits Go Kernelized will be presented at European Workshop on Reinforcement Learning (EWRL 2024).
September 2024: Kernel-Based Function Approximation for Average Reward Reinforcement Learning: An Optimist No-Regret Algorithm will be presented at European Workshop on Reinforcement Learning (EWRL 2024).
July 2024: Giving a tutorial on Recent Advances of Statistical Reinforcement Learning at Uncertainty in Artificial Intelligence (UAI) 2024, July 15th in Barcelona. [Download the slides here].
June 2024: Involved in organizing a local ICML meetup on July 12th in London. A great opportunity to present your work, learn, and grow your network.
June 2024: Open Problem: Order Optimal Regret Bounds for Kernel-Based Reinforcement Learning is accepted at COLT 2024.
June 2024: Reward-Free Kernel-Based Reinforcement Learning is accepted at ICML 2024.
June 2024: Random Exploration in Bayesian Optimization: Order-Optimal Regret and Computational Efficiency is accepted at ICML 2024.
April 2024: Giving a tutorial on Recent Advances of Statistical Reinforcement Learning at Uncertainty in Artificial Intelligence (UAI) 2024, July 15th in Barcelona.
December 2023: Optimal Regret Bounds for Collaborative Learning in Bandits is accepted at Algorithmic Learning Theory (ALT) 2024.
December 2023: Adversarial Contextual Bandits Go Kernelized is accepted at Algorithmic Learning Theory (ALT) 2024.
December 2023: Presenting our NeurIPS paper at local meetup, Cambrdige University, Dec 8th.
October 2023: Collaborative Learning in Kernel-based Bandits for Distributed Users is accepted at IEEE Transactions on Signal Processing.
October 2023: Giving a talk at the Inria Scool seminar series at University of Lille.
October 2023: Adversarial Contextual Bandits Go Kernelized is available on arXiv.
September 2023: Kernelized Reinforcement Learning with Order Optimal Regret Bounds is accepted at NeurIPS 2023.
August 2023: Generative Diffusion Models for Radio Wireless Channel Modelling and Sampling is accepted at GLOBECOM 2023.
August 2023: Kernelized Reinforcement Learning with Order Optimal Regret Bounds is accepted at EWRL 2023.
August 2023: Check out Tor Lattimore's response to the open problem on online confidence intervals for RKHS elemets.
July 2023: Giving an online lecture at FeDucation seminar series (Florida International University).
June 2023: Giving a seminar on kernel-based reinforcement learning at Deepmind/Ellis CSML seminar series.
June 2023: Presenting Information Gain and Uniform Generalization Bounds for Neural Kernel Models at ISIT 2023 , Taipei.
May 2023: Giving an invited talk on kernel-based RL at the London Symposium on Information Theory
April 2023: "Delayed Feedback in Kernel Bandits" is accepted at ICML 2023.
April 2023: "Provably and Practically Efficient Neural Contextual Bandits" is accepted at ICML 2023.
April 2023: "Image generation with shortest path diffusion" is accepted at ICML 2023.
Feburary 2023: "Delayed Feedback in Kernel Bandits" is available on arXiv.
January 2023: "Sample Complexity of Kernel-Based Q-Learning" is accepted at AISTATS 2023.
January 2023: "Fisher-Legendre (FishLeg) optimization of deep neural networks" is accepted at ICLR 2023.
December 2022: Presenting "Gradient Descent: Robustness to Adversarial Corruption" at OPT2022 workshop at NeurIPS 2022, New Orleans.
October 2022: "Near-Optimal Collaborative Learning in Bandits" has been designated as an Oral presentation at NeurIPS 2022.
July 2022: Presenting an open problem on noise-free kernel-based bandit at COLT 2022, London.
May 2022: "Provably and Practically Efficient Neural Contextual Bandits" is available on arXiv.
May 2022: "Near-Optimal Collaborative Learning in Bandits" is available on arXiv.
May 2022: "Improved Convergence Rates for Sparse Approximation Methods in Kernel-Based Learning" is accepted at ICML 2022 for a Spotlight presentation.
October 2021: "Scalable Thompson Sampling using Sparse Gaussian Process Models" is accepted at NeurIPS 2021.
October 2021: "A Domain-Shrinking based Bayesian Optimization Algorithm with Order-Optimal Regret Performance" is accepted at NeurIPS 2021.
October 2021: "Optimal Order Simple Regret for Gaussian Process Bandits" is accepted at NeurIPS 2021.
August 2021: Moderating the "Bandits, RL and Control" session at COLT 2021.
August 2021: Presenting "Tight Online Confidence Intervals for RKHS Elements" at COLT 2021.
January 2021: "On Information Gain and Regret Bounds in Gaussian Process Bandits" is accepted to be presented at AIStats 2021.