no code implementations • 4 Oct 2023 • Bekzhan Kerimkulov, James-Michael Leahy, David Siska, Lukasz Szpruch, Yufei Zhang
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.
no code implementations • 31 Aug 2023 • Carsten Maple, Lukasz Szpruch, Gregory Epiphaniou, Kalina Staykova, Simran Singh, William Penwarden, Yisi Wen, Zijian Wang, Jagdish Hariharan, Pavle Avramovic
A further issue identified in this report is the systemic risk that AI can introduce to the financial sector.
no code implementations • 14 Aug 2023 • Tanut Treetanthiploet, Yufei Zhang, Lukasz Szpruch, Isaac Bowers-Barnard, Henrietta Ridley, James Hickey, Chris Pearce
The emergence of price comparison websites (PCWs) has presented insurers with unique challenges in formulating effective pricing strategies.
2 code implementations • 12 Nov 2022 • Florimond Houssiau, James Jordon, Samuel N. Cohen, Owen Daniel, Andrew Elliott, James Geddes, Callum Mole, Camila Rangel-Smith, Lukasz Szpruch
We here present TAPAS, a toolbox of attacks to evaluate synthetic data privacy under a wide range of scenarios.
no code implementations • 8 Aug 2022 • Lukasz Szpruch, Tanut Treetanthiploet, Yufei Zhang
This work uses the entropy-regularised relaxed stochastic control perspective as a principled framework for designing reinforcement learning (RL) algorithms.
no code implementations • 6 May 2022 • James Jordon, Lukasz Szpruch, Florimond Houssiau, Mirko Bottarelli, Giovanni Cherubin, Carsten Maple, Samuel N. Cohen, Adrian Weller
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.
no code implementations • 18 Jan 2022 • Bekzhan Kerimkulov, James-Michael Leahy, David Šiška, Lukasz Szpruch
We show that the objective function is increasing along the gradient flow.
no code implementations • 19 Dec 2021 • Lukasz Szpruch, Tanut Treetanthiploet, Yufei Zhang
We develop a probabilistic framework for analysing model-based reinforcement learning in the episodic setting.
Model-based Reinforcement Learning Reinforcement Learning (RL)
1 code implementation • 1 Nov 2021 • Hao Ni, Lukasz Szpruch, Marc Sabate-Vidales, Baoren Xiao, Magnus Wiese, Shujian Liao
Synthetic data is an emerging technology that can significantly accelerate the development and deployment of AI machine learning pipelines.
no code implementations • NeurIPS 2021 • Haoyang Cao, Samuel N. Cohen, Lukasz Szpruch
Inverse reinforcement learning attempts to reconstruct the reward function in a Markov decision problem, using observations of agent actions.
no code implementations • 9 Feb 2021 • Samuel N. Cohen, Derek Snow, Lukasz Szpruch
Machine learning models are increasingly used in a wide variety of financial settings.
1 code implementation • 8 Jul 2020 • Patryk Gierjatowicz, Marc Sabate-Vidales, David Šiška, Lukasz Szpruch, Žan Žurič
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.
2 code implementations • 9 Jun 2020 • Shujian Liao, Hao Ni, Lukasz Szpruch, Magnus Wiese, Marc Sabate-Vidales, Baoren Xiao
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.
no code implementations • 30 May 2020 • Imanol Perez Arribas, Cristopher Salvi, Lukasz Szpruch
Mathematical models, calibrated to data, have become ubiquitous to make key decision processes in modern quantitative finance.
no code implementations • 19 May 2019 • Kaitong Hu, Zhenjie Ren, David Siska, Lukasz Szpruch
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.
2 code implementations • 11 Oct 2018 • Marc Sabate Vidales, David Siska, Lukasz Szpruch
We develop several deep learning algorithms for approximating families of parametric PDE solutions.
no code implementations • 21 Aug 2018 • Mateusz B. Majka, Aleksandar Mijatović, Lukasz Szpruch
Finally, we provide a weak convergence analysis that covers both the standard and the randomised (inaccurate) drift case.
no code implementations • 15 Sep 2016 • Mike Giles, Tigran Nagapetyan, Lukasz Szpruch, Sebastian Vollmer, Konstantinos Zygalakis
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.
no code implementations • 4 May 2016 • Michael B. Giles, Mateusz B. Majka, Lukasz Szpruch, Sebastian Vollmer, Konstantinos Zygalakis
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.