arXiv research

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

New framework for policy gradient methods in continuous time reinforcement learning.

Private machine learning framework using randomised response.

We design a randomised parallel version of Adaboost based on previous studies on parallel coordinate descent. The algorithm uses the fact that the logarithm of the exponential loss is a function with coordinate-wise Lipschitz continuous gradient, in order to define the step lengths. We provide the proof of convergence …

New method improves calibration of BayesCG for better uncertainty quantification.

New method uses randomised signatures for generating financial time series data.

Randomised classifiers outperform deterministic ones in strategic classification.

FP uses random projections to train networks without feedback, achieving comparable performance to backpropagation.

Numerous kinds of uncertainties may affect an economy, e.g. economic, political, and environmental ones. We model the aggregate impact by the uncertainties on an economy and its associated financial market by randomised mixtures of Lévy processes. We assume that market participants observe the randomised mixtures only …

New bounds for model generalization under deterministic gradient descent.

We extend previous large deviations results for the randomised Heston model to the case of moderate deviations. The proofs involve the Gärtner-Ellis theorem and sharp large deviations tools.

Study uses actor-critic method for continuous-time mean-field control with entropy regularisation.

New algorithm improves game learning with randomised optimism.

We propose a randomised version of the Heston model-a widely used stochastic volatility model in mathematical finance-assuming that the starting point of the variance process is a random variable. In such a system, we study the small-and large-time behaviours of the implied volatility, and show that the proposed random…

Paper develops a privacy-preserving nonparametric regression method.

Randomized exploration in linear bandits achieves optimal regret bounds.

Improved Bayesian optimisation method using randomised Gaussian process UCB.

Discrete time analogues of ergodic stochastic differential equations (SDEs) are one of the most popular and flexible tools for sampling high-dimensional probability measures. Non-asymptotic analysis in the $L^2$ Wasserstein distance of sampling algorithms based on Euler discretisations of SDEs has been recently develop…

We develop a new Monte Carlo variance reduction method to estimate the expectation of two commonly encountered path-dependent functionals: first-passage times and occupation times of sets. The method is based on a recursive approximation of the first-passage time probability and expected occupation time of sets of a Le…

New method optimizes experimental design for specific applications.

Improved sampling efficiency with Random Reshuffling for Langevin dynamics.

Two modified tests improve the reliability of evaluating explanation methods.

New method estimates nested expectations with biased and antithetic sampling.

EVILL uses randomised perturbations to improve exploration in bandit problems.

Estimates long-term effects from short-term experiments and observational data with unobserved confounders.

New minibatching strategy reduces stochastic gradient bias in optimisation.

New bounds for shallow neural networks with deterministic parameters.

In this paper we propose a Bayesian method for estimating architectural parameters of neural networks, namely layer size and network depth. We do this by learning concrete distributions over these parameters. Our results show that regular networks with a learnt structure can generalise better on small datasets, while f…

Improved control approach for correlated bandits with better performance.

We introduce Bayesian least-squares policy iteration (BLSPI), an off-policy, model-free, policy iteration algorithm that uses the Bayesian least-squares temporal-difference (BLSTD) learning algorithm to evaluate policies. An online variant of BLSPI has been also proposed, called randomised BLSPI (RBLSPI), that improves…

We consider the problem of link prediction, based on partial observation of a large network, and on side information associated to its vertices. The generative model is formulated as a matrix logistic regression. The performance of the model is analysed in a high-dimensional regime under a structural assumption. The mi…

New method uses neural networks for optimal stopping time problems.

Popular approaches to differential privacy, such as the Laplace and exponential mechanisms, calibrate randomised smoothing through global sensitivity of the target non-private function. Bounding such sensitivity is often a prohibitively complex analytic calculation. As an alternative, we propose a straightforward sampl…

We develop a monitoring procedure to detect changes in a large approximate factor model. Letting $r$ be the number of common factors, we base our statistics on the fact that the $\left( r+1\right)$-th eigenvalue of the sample covariance matrix is bounded under the null of no change, whereas it becomes spiked under cha…

This paper tackles batch Bayesian optimal experimental design by using Wasserstein gradient flows.

We propose and evaluate alternative ensemble schemes for a new instance based learning classifier, the Randomised Sphere Cover (RSC) classifier. RSC fuses instances into spheres, then bases classification on distance to spheres rather than distance to instances. The randomised nature of RSC makes it ideal for use in en…

In recent years, sparse principal component analysis has emerged as an extremely popular dimension reduction technique for high-dimensional data. The theoretical challenge, in the simplest case, is to estimate the leading eigenvector of a population covariance matrix under the assumption that this eigenvector is sparse…

Develops a kernel-based framework for dynamic trading strategies.

Novel strategy for federated learning with privacy-preserving predictors and nonvacuous generalization bounds.

Automated PDE discovery from multiple noisy experiments.

We consider classification in the presence of class-dependent asymmetric label noise with unknown noise probabilities. In this setting, identifiability conditions are known, but additional assumptions were shown to be required for finite sample rates, and so far only the parametric rate has been obtained. Assuming thes…

Study proves value of non-Markovian games with partial, asymmetric info.

Paper improves privacy bounds for shuffle model using novel numerical techniques.

Machine learning experiments often mislead due to unmet assumptions.

An explorative data analysis system should be aware of what the user already knows and what the user wants to know of the data: otherwise the system cannot provide the user with the most informative and useful views of the data. We propose a principled way to do exploratory data analysis, where the user's background kn…

Neural networks have been widely used as predictive models to fit data distribution, and they could be implemented through learning a collection of samples. In many applications, however, the given dataset may contain noisy samples or outliers which may result in a poor learner model in terms of generalization. This pa…

The paper proposes an estimator to make inference of heterogeneous treatment effects sorted by impact groups (GATES) for non-randomised experiments. The groups can be understood as a broader aggregation of the conditional average treatment effect (CATE) where the number of groups is set in advance. In economics, this a…

Theoretical limits show experimental data can falsify but not validate causal estimates from observational studies.