Search Results for author:
Found 19 papers, 5 papers with code
A Fisher-Rao gradient flow for entropy-regularised Markov decision processes in Polish spaces
We study the global convergence of a Fisher-Rao policy gradient flow for infinite-horizon entropy-regularised Markov decision processes with Polish state and action space.
The AI Revolution: Opportunities and Challenges for the Finance Sector
A further issue identified in this report is the systemic risk that AI can introduce to the financial sector.
Insurance pricing on price comparison websites via reinforcement learning
The emergence of price comparison websites (PCWs) has presented insurers with unique challenges in formulating effective pricing strategies.
TAPAS: a Toolbox for Adversarial Privacy Auditing of Synthetic Data
We here present TAPAS, a toolbox of attacks to evaluate synthetic data privacy under a wide range of scenarios.
Optimal scheduling of entropy regulariser for continuous-time linear-quadratic reinforcement learning
This work uses the entropy-regularised relaxed stochastic control perspective as a principled framework for designing reinforcement learning (RL) algorithms.
Synthetic Data -- what, why and how?
This explainer document aims to provide an overview of the current state of the rapidly expanding work on synthetic data technologies, with a particular focus on privacy.
Convergence of Policy Gradient for Entropy Regularized MDPs with Neural Network Approximation in the Mean-Field Regime
We show that the objective function is increasing along the gradient flow.
Exploration-exploitation trade-off for continuous-time episodic reinforcement learning with linear-convex models
We develop a probabilistic framework for analysing model-based reinforcement learning in the episodic setting.
Model-based Reinforcement Learning
Reinforcement Learning (RL)
Sig-Wasserstein GANs for Time Series Generation
Synthetic data is an emerging technology that can significantly accelerate the development and deployment of AI machine learning pipelines.
Identifiability in inverse reinforcement learning
Inverse reinforcement learning attempts to reconstruct the reward function in a Markov decision problem, using observations of agent actions.
Black-box model risk in finance
Machine learning models are increasingly used in a wide variety of financial settings.
Robust pricing and hedging via neural SDEs
Combining neural networks with risk models based on classical stochastic differential equations (SDEs), we find robust bounds for prices of derivatives and the corresponding hedging strategies while incorporating relevant market data.
Conditional Sig-Wasserstein GANs for Time Series Generation
The signature of a path is a graded sequence of statistics that provides a universal description for a stream of data, and its expected value characterises the law of the time-series model.
Sig-SDEs model for quantitative finance
Mathematical models, calibrated to data, have become ubiquitous to make key decision processes in modern quantitative finance.
Mean-Field Langevin Dynamics and Energy Landscape of Neural Networks
Our work is motivated by a desire to study the theoretical underpinning for the convergence of stochastic gradient type algorithms widely used for non-convex learning tasks such as training of neural networks.
Unbiased deep solvers for linear parametric PDEs
We develop several deep learning algorithms for approximating families of parametric PDE solutions.
Non-asymptotic bounds for sampling algorithms without log-concavity
Finally, we provide a weak convergence analysis that covers both the standard and the randomised (inaccurate) drift case.
Multilevel Monte Carlo for Scalable Bayesian Computations
In contrast to MCMC methods, Stochastic Gradient MCMC (SGMCMC) algorithms such as the Stochastic Gradient Langevin Dynamics (SGLD) only require access to a batch of the data set at every step.
Multilevel Monte Carlo methods for the approximation of invariant measures of stochastic differential equations
We show that this is the first stochastic gradient MCMC method with complexity $\mathcal{O}(\varepsilon^{-2}|\log {\varepsilon}|^{3})$, in contrast to the complexity $\mathcal{O}(\varepsilon^{-3})$ of currently available methods.
