arXiv research

Extends moderate deviations for a randomised Heston model.

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

Private machine learning framework using randomised response.

Randomised classifiers outperform deterministic ones in strategic classification.

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

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…

Randomized exploration in linear bandits achieves optimal regret bounds.

Improved Bayesian optimisation method using randomised Gaussian process UCB.

Two modified tests improve the reliability of evaluating explanation methods.

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 …

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 …

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

New method improves calibration of BayesCG for better uncertainty quantification.

Improved control approach for correlated bandits with better performance.

New bounds for sampling algorithms without log-concavity assumptions.

New method optimizes experimental design for specific applications.

A new algorithm improves policy discovery in uncertain environments.

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…

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…

EVILL uses randomised perturbations to improve exploration in bandit problems.

Paper develops a privacy-preserving nonparametric regression method.

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

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

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

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

Framework guides user exploration of data relations.

New method estimates nested expectations with biased and antithetic sampling.

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…

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…

Paper defines saddle points in asymmetric Dynkin games using martingale theory.

Bayesian method learns neural network architecture parameters.

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

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…

Classical (Itô diffusions) stochastic volatility models are not able to capture the steepness of small-maturity implied volatility smiles. Jumps, in particular exponential Lévy and affine models, which exhibit small-maturity exploding smiles, have historically been proposed to remedy this (see \cite{Tank} for an overvi…

New bounds for model generalization under deterministic gradient descent.

The generation of artificial data based on existing observations, known as data augmentation, is a technique used in machine learning to improve model accuracy, generalisation, and to control overfitting. Augmentor is a software package, available in both Python and Julia versions, that provides a high level API for th…

Study generalization of voting classifiers using margin-based bounds.

New bounds for shallow neural networks with deterministic parameters.

American options in a multi-asset market model with proportional transaction costs are studied in the case when the holder of an option is able to exercise it gradually at a so-called mixed (randomised) stopping time. The introduction of gradual exercise leads to tighter bounds on the option price when compared to the …

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…

Game (Israeli) options in a multi-asset market model with proportional transaction costs are studied in the case when the buyer is allowed to exercise the option and the seller has the right to cancel the option gradually at a mixed (or randomised) stopping time, rather than instantly at an ordinary stopping time. Allo…

New method uses neural networks for optimal stopping time problems.

Study compares shareholder networks in Turkish and Dutch companies.

Automated PDE discovery from multiple noisy experiments.

We price and hedge American options robustly in continuous time.

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

No real-world reward function is perfect. Sensory errors and software bugs may result in RL agents observing higher (or lower) rewards than they should. For example, a reinforcement learning agent may prefer states where a sensory error gives it the maximum reward, but where the true reward is actually small. We formal…