arXiv research

Book covers tools for zeroth-order convex optimisation.

Improved regret bound for adversarial bandit convex optimisation.

This paper explores optimising acquisition functions in Bayesian optimisation.

New method finds better arbitrage opportunities in AMMs.

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.

SOBER optimizes and quadrates efficiently in parallel for diverse tasks.

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…

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

New method optimizes multiple points in Bayesian optimization efficiently.

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

Novel algorithms for entropic optimal transport from an optimisation perspective.

Unified framework for lifted training and inversion of neural networks.

RL models outperform traditional methods in certain market conditions.

The inverse Ising problem seeks to reconstruct the parameters of an Ising Hamiltonian on the basis of spin configurations sampled from the Boltzmann measure. Over the last decade, many applications of the inverse Ising problem have arisen, driven by the advent of large-scale data across different scientific disciplines…

New research challenges the independence assumption in neurosymbolic learning, leading to overconfident predictions and unrepresentable uncertainty.

A new optimisation framework for neural networks without hyperparameters.

New algorithm reduces regret in stochastic bandit convex optimization.

In this work we study convex relaxations of quadratic optimisation problems over permutation matrices. While existing semidefinite programming approaches can achieve remarkably tight relaxations, they have the strong disadvantage that they lift the original $n {\times} n$-dimensional variable to an $n^2 {\times} n^2$-d…

Gradient descent performs well on weakly convex losses, offering generalization guarantees.

Simplifies noisy convex optimization with a new algorithm.

A new model learns graph structures from data.

New algorithms for sampling in constrained domains without learning rates.

New algorithm finds sparse matrices on Stiefel manifold for optimisation.

Develops a new method for risk diversification using dynamic risk measures.

In this paper, we study a semi-martingale optimal transport problem and its application to the calibration of Local-Stochastic Volatility (LSV) models. Rather than considering the classical constraints on marginal distributions at initial and final time, we optimise our cost function given the prices of a finite number…

In this work we introduce a new optimisation method called SAGA in the spirit of SAG, SDCA, MISO and SVRG, a set of recently proposed incremental gradient algorithms with fast linear convergence rates. SAGA improves on the theory behind SAG and SVRG, with better theoretical convergence rates, and has support for compos…

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.…

New minibatching strategy reduces stochastic gradient bias in optimisation.

Investors face constraints in Heston's model; optimal allocation differs from naive capped strategy.

An important task in machine learning and statistics is the approximation of a probability measure by an empirical measure supported on a discrete point set. Stein Points are a class of algorithms for this task, which proceed by sequentially minimising a Stein discrepancy between the empirical measure and the target an…

In this paper we develop proximal methods for statistical learning. Proximal point algorithms are useful in statistics and machine learning for obtaining optimization solutions for composite functions. Our approach exploits closed-form solutions of proximal operators and envelope representations based on the Moreau, Fo…

Unified theory linking Bayesian and ensemble methods in deep learning.

New framework converts multi-objective to single-objective optimisation.

Unified Bayesian Optimisation for mixed variables improves performance.

A new method learns priors for Bayesian optimisation to improve performance.

Study improves Bayesian optimisation with ensemble transfer learning.

New principles for collapsing law-invariant functionals to means, extending beyond convexity.

AdamZ optimiser improves neural network training efficiency.

Wind farm layout optimisation tackles space constraints with Bayesian multi-objective approach.

Adaptive importance samplers are adaptive Monte Carlo algorithms to estimate expectations with respect to some target distribution which \textit{adapt} themselves to obtain better estimators over a sequence of iterations. Although it is straightforward to show that they have the same $\mathcal{O}(1/\sqrt{N})$ convergen…

Bayesian optimisation tackles high-dimensional categorical and mixed search spaces.

O3 optimizes samples from generative models without extra training.

This paper improves inverse problem solving with weakly convex regularisers and proves convergence.

Bayesian optimisation framework for graph functions.

Bayesian optimisation tackles expensive black-box functions with constraints.

MTL2L learns to adapt optimisation rules for unseen data.