arXiv research

Improved regret bound for adversarial bandit convex optimisation.

Book covers tools for zeroth-order convex optimisation.

Efficient algorithm for zeroth-order bandit convex optimization with bounds on regret.

New algorithm reduces regret in stochastic bandit convex optimization.

The information-theoretic analysis by Russo and Van Roy (2014) in combination with minimax duality has proved a powerful tool for the analysis of online learning algorithms in full and partial information settings. In most applications there is a tantalising similarity to the classical analysis based on mirror descent.…

We describe a novel algorithm for noisy global optimisation and continuum-armed bandits, with good convergence properties over any continuous reward function having finitely many polynomial maxima. Over such functions, our algorithm achieves square-root regret in bandits, and inverse-square-root error in optimisation, …

We consider the problem of optimising functions in the reproducing kernel Hilbert space (RKHS) of a Matérn kernel with smoothness parameter $ν$ over the domain $[0,1]^d$ under noisy bandit feedback. Our contribution, the $π$-GP-UCB algorithm, is the first practical approach with guaranteed sublinear regret for all $ν>1…

Pure exploration (aka active testing) is the fundamental task of sequentially gathering information to answer a query about a stochastic environment. Good algorithms make few mistakes and take few samples. Lower bounds (for multi-armed bandit models with arms in an exponential family) reveal that the sample complexity …

Applying causal inference models in areas such as economics, healthcare and marketing receives great interest from the machine learning community. In particular, estimating the individual-treatment-effect (ITE) in settings such as precision medicine and targeted advertising has peaked in application. Optimising this IT…

Unified Bayesian Optimisation for mixed variables improves performance.

New methods for efficient exploration under unknown linear constraints in bandits.

This paper explores optimising acquisition functions in Bayesian optimisation.

FraPPE efficiently identifies Pareto optimal arms in multi-objective bandits.

New algorithm optimizes noisy function evaluations with delayed feedback.

Efficient optimisation of black-box problems that comprise both continuous and categorical inputs is important, yet poses significant challenges. We propose a new approach, Continuous and Categorical Bayesian Optimisation (CoCaBO), which combines the strengths of multi-armed bandits and Bayesian optimisation to select …

New method finds better arbitrage opportunities in AMMs.

New algorithms reduce regret for convex bandits with small comparator norms.

Optimal switching regret for all segmentations in online convex optimisation.

Unified high-probability regret bounds for online convex optimisation with randomised gradient estimators.

Paper develops robust SGLD for solving non-convex DRO problems.

Optimal best arm identification for multi-objective bandits with fixed error probability.

RONM method reduces regret in stochastic convex bandits with decreasing noise.

Stochastic linear bandits are a natural and simple generalisation of finite-armed bandits with numerous practical applications. Current approaches focus on generalising existing techniques for finite-armed bandits, notably the optimism principle and Thompson sampling. While prior work has mostly been in the worst-case …

SOBER optimizes and quadrates efficiently in parallel for diverse tasks.

Bandit methods for black-box optimisation, such as Bayesian optimisation, are used in a variety of applications including hyper-parameter tuning and experiment design. Recently, \emph{multi-fidelity} methods have garnered considerable attention since function evaluations have become increasingly expensive in such appli…

Improves bandit convex optimization with gradient variations.

We consider the problem of inverse kinematics (IK), where one wants to find the parameters of a given kinematic skeleton that best explain a set of observed 3D joint locations. The kinematic skeleton has a tree structure, where each node is a joint that has an associated geometric transformation that is propagated to a…

The paper tackles minimax optimality in continuum contextual bandits with Hölder continuity.

The dueling bandit is a learning framework wherein the feedback information in the learning process is restricted to a noisy comparison between a pair of actions. In this research, we address a dueling bandit problem based on a cost function over a continuous space. We propose a stochastic mirror descent algorithm and …

Adaptive Bayesian learning agent for non-stationary bandits.

Study tackles non-stationary bandit convex optimization with new algorithms.

Paper tackles federated learning with personalised bandit algorithms.

New method optimizes multiple points in Bayesian optimization efficiently.

ARC algorithm optimizes dynamic pricing with correlated observations.

We introduce a novel framework for the estimation of the posterior distribution over the weights of a neural network, based on a new probabilistic interpretation of adaptive optimisation algorithms such as AdaGrad and Adam. We demonstrate the effectiveness of our Bayesian Adam method, Badam, by experimentally showing t…

A new optimisation method efficiently scales Hessian-vector products for neural networks.

We introduce the functional bandit problem, where the objective is to find an arm that optimises a known functional of the unknown arm-reward distributions. These problems arise in many settings such as maximum entropy methods in natural language processing, and risk-averse decision-making, but current best-arm identif…

New algorithm reduces regret in bandit optimization for high-dimensional data.

Novel algorithms for entropic optimal transport from an optimisation perspective.

This paper improves offline contextual bandits using distributional robustness.

Unified framework for lifted training and inversion of neural networks.

Bayesian Optimisation (BO) is a technique used in optimising a $D$-dimensional function which is typically expensive to evaluate. While there have been many successes for BO in low dimensions, scaling it to high dimensions has been notoriously difficult. Existing literature on the topic are under very restrictive setti…

RL models outperform traditional methods in certain market conditions.

We provide a simple and efficient algorithm for adversarial $k$-action $d$-outcome non-degenerate locally observable partial monitoring game for which the $n$-round minimax regret is bounded by $6(d+1) k^{3/2} \sqrt{n \log(k)}$, matching the best known information-theoretic upper bound. The same algorithm also achieves…

Motivated by applications in clinical trials and finance, we study the problem of online convex optimization (with bandit feedback) where the decision maker is risk-averse. We provide two algorithms to solve this problem. The first one is a descent-type algorithm which is easy to implement. The second algorithm, which …

Unified framework for analyzing online convex optimization across various settings.

Paper tackles LDP bandits learning with improved results and sub-linear regret.

Randomized exploration in linear bandits achieves optimal regret bounds.