Zobrazeno 1 - 10
of 1 053
pro vyhledávání: '"P. Warin"'
We demonstrate that automatic differentiation, which has become commonly available in machine learning frameworks, is an efficient way to explore ideas that lead to algorithmic improvement in multi-scale affine image registration and affine super-res
Externí odkaz:
http://arxiv.org/abs/2411.02806
Rahimi and Recht [31] introduced the idea of decomposing shift-invariant kernels by randomly sampling from their spectral distribution. This famous technique, known as Random Fourier Features (RFF), is in principle applicable to any shift-invariant k
Externí odkaz:
http://arxiv.org/abs/2411.02770
Autor:
Warin, Xavier
A new Kolmogorov-Arnold network (KAN) is proposed to approximate potentially irregular functions in high dimension. We show that it outperforms multilayer perceptrons in terms of accuracy and converges faster. We also compare it with several proposed
Externí odkaz:
http://arxiv.org/abs/2410.03801
We propose a comprehensive framework for policy gradient methods tailored to continuous time reinforcement learning. This is based on the connection between stochastic control problems and randomised problems, enabling applications across various cla
Externí odkaz:
http://arxiv.org/abs/2404.17939
Autor:
Bokanowski, Olivier, Warin, Xavier
We study deterministic optimal control problems for differential games with finite horizon. We propose new approximations of the strategies in feedback form, and show error estimates and a convergence result of the value in some weak sense for one of
Externí odkaz:
http://arxiv.org/abs/2402.02792
In this paper, we introduce various machine learning solvers for (coupled) forward-backward systems of stochastic differential equations (FBSDEs) driven by a Brownian motion and a Poisson random measure. We provide a rigorous comparison of the differ
Externí odkaz:
http://arxiv.org/abs/2401.03245
Autor:
Pham, Huyên, Warin, Xavier
We develop a new policy gradient and actor-critic algorithm for solving mean-field control problems within a continuous time reinforcement learning setting. Our approach leverages a gradient-based representation of the value function, employing param
Externí odkaz:
http://arxiv.org/abs/2309.04317
Autor:
Deschatre, Thomas, Warin, Xavier
In this paper, we propose a multidimensional statistical model of intraday electricity prices at the scale of the trading session, which allows all products to be simulated simultaneously. This model, based on Poisson measures and inspired by the Com
Externí odkaz:
http://arxiv.org/abs/2307.16619
Autor:
Warin, Xavier
We study news neural networks to approximate function of distributions in a probability space. Two classes of neural networks based on quantile and moment approximation are proposed to learn these functions and are theoretically supported by universa
Externí odkaz:
http://arxiv.org/abs/2303.11060
Autor:
Pham, Huyên, Warin, Xavier
This paper is devoted to the numerical resolution of McKean-Vlasov control problems via the class of mean-field neural networks introduced in our companion paper [25] in order to learn the solution on the Wasserstein space. We propose several algorit
Externí odkaz:
http://arxiv.org/abs/2212.11518