Arrow Research search

Author name cluster

Hamish Flynn

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

5 papers
1 author row

Possible papers

5

EWRL Workshop 2025 Workshop Paper

Linear Bandits with Non-i. i. d. Noise

  • Baptiste Abélès
  • Eugenio Clerico
  • Hamish Flynn
  • Gergely Neu

We study the linear stochastic bandit problem, relaxing the standard i. i. d. ~assumption on the observation noise. As an alternative to this restrictive assumption, we allow the noise terms across rounds to be sub-Gaussian but interdependent, with dependencies that decay over time. To address this setting, we develop new confidence sequences using a recently introduced reduction scheme to sequential probability assignment, and use these to derive a bandit algorithm based on the principle of optimism in the face of uncertainty. We provide regret bounds for the resulting algorithm, expressed in terms of the decay rate of the strength of dependence between observations. Among other results, we show that our bounds recover the standard rates up to a factor of the mixing time for geometrically mixing observation noise.

PDF

EWRL Workshop 2025 Workshop Paper

Sparse Nonparametric Contextual Bandits

  • Hamish Flynn
  • Julia Olkhovskaya
  • Paul Rognon-Vael

We study the benefits of sparsity in nonparametric contextual bandit problems, in which the set of candidate features is countably or uncountably infinite. Our contribution is two-fold. First, using a novel reduction to sequences of multi-armed bandit problems, we provide lower bounds on the minimax regret, which show that polynomial dependence on the number of actions is generally unavoidable in this setting. Second, we show that a variant of the Feel-Good Thompson Sampling algorithm enjoys regret bounds that match our lower bounds up to logarithmic factors of the horizon, and have logarithmic dependence on the effective number of candidate features. When we apply our results to kernelised and neural contextual bandits, we find that sparsity enables better regret bounds whenever the horizon is large enough relative to the sparsity and the number of actions.

PDF

EWRL Workshop 2025 Workshop Paper

Sparse Optimistic Information Directed Sampling

  • Ludovic Schwartz
  • Hamish Flynn
  • Gergely Neu

Many high-dimensional online decision-making problems can be modeled as stochastic sparse linear bandits. Most existing algorithms are designed to achieve optimal worst-case regret in either the data-rich regime, where polynomial dependence on the ambient dimension is unavoidable, or the data-poor regime, where dimension-independence is possible at the cost of worse dependence on the number of rounds. In contrast, the Bayesian approach of Information Directed Sampling (IDS) achieves the best of both worlds: a Bayesian regret bound that has the optimal rate in both regimes simultaneously. In this work, we explore the use of Sparse Optimistic Information Directed Sampling (SOIDS) to achieve the best of both worlds in the worst-case setting, without Bayesian assumptions. Through a novel analysis that enables the use of a time-dependent learning rate, we show that OIDS can be tuned without prior knowledge to optimally balance information and regret. Our results extend the theoretical guarantees of IDS, providing the first algorithm that simultaneously achieves optimal worst-case regret in both the data-rich and data-poor regimes. We empirically demonstrate the good performance of SOIDS.

PDF

NeurIPS Conference 2025 Conference Paper

Sparse Optimistic Information Directed Sampling

  • Ludovic Schwartz
  • Hamish Flynn
  • Gergely Neu

Many high-dimensional online decision-making problems can be modeled as stochastic sparse linear bandits. Most existing algorithms are designed to achieve optimal worst-case regret in either the data-rich regime, where polynomial dependence on the ambient dimension is unavoidable, or the data-poor regime, where dimension-independence is possible at the cost of worse dependence on the number of rounds. In contrast, the Bayesian approach of Information Directed Sampling (IDS) achieves the best of both worlds: a Bayesian regret bound that has the optimal rate in both regimes simultaneously. In this work, we explore the use of Sparse Optimistic Information Directed Sampling (SOIDS) to achieve the best of both worlds in the worst-case setting, without Bayesian assumptions. Through a novel analysis that enables the use of a time-dependent learning rate, we show that OIDS can be tuned without prior knowledge to optimally balance information and regret. Our results extend the theoretical guarantees of IDS, providing the first algorithm that simultaneously achieves optimal worst-case regret in both the data-rich and data-poor regimes. We empirically demonstrate the good performance of SOIDS.

PDF Details

NeurIPS Conference 2023 Conference Paper

Improved Algorithms for Stochastic Linear Bandits Using Tail Bounds for Martingale Mixtures

  • Hamish Flynn
  • David Reeb
  • Melih Kandemir
  • Jan R. Peters

We present improved algorithms with worst-case regret guarantees for the stochastic linear bandit problem. The widely used "optimism in the face of uncertainty" principle reduces a stochastic bandit problem to the construction of a confidence sequence for the unknown reward function. The performance of the resulting bandit algorithm depends on the size of the confidence sequence, with smaller confidence sets yielding better empirical performance and stronger regret guarantees. In this work, we use a novel tail bound for adaptive martingale mixtures to construct confidence sequences which are suitable for stochastic bandits. These confidence sequences allow for efficient action selection via convex programming. We prove that a linear bandit algorithm based on our confidence sequences is guaranteed to achieve competitive worst-case regret. We show that our confidence sequences are tighter than competitors, both empirically and theoretically. Finally, we demonstrate that our tighter confidence sequences give improved performance in several hyperparameter tuning tasks.

PDF Details
v2026.09.13