paper-with-me

Papers

Convergence proofs and strong error bounds for forward-backward stochastic differential equations using neural network simulations

2024-11-02 · Oliver Sheridan-Methven

We introduce forward-backward stochastic differential equations, highlighting the connection between solutions of these and solutions of partial differential equations, related by the Feynman-Kac theorem. We review the technique of approximating solutions to high dimensional partial differential equations using neural networks, and similarly approximating solutions of stochastic differential equations using multilevel Monte Carlo. Connecting the multilevel Monte Carlo method with the neural network framework using the setup established by E et al. and Raissi, we provide novel numerical analyses to produce strong error bounds for the specific framework of Raissi. Our results bound the overall strong error in terms of the maximum of the discretisation error and the neural network's approximation error. Our analyses are necessary for applications of multilevel Monte Carlo, for which we propose suitable frameworks to exploit the variance structures of the multilevel estimators we elucidate. Also, focusing on the loss function advocated by Raissi, we expose the limitations of this, highlighting and quantifying its bias and variance. Lastly, we propose various avenues of further research which we anticipate should offer significant insight and speed improvements.

📄 PDF Abstract BibTeX arXiv:2411.01306

Code (0)

등록된 구현이 없습니다.

Methods 이 논문이 사용한 방법론

SPEED The monocular depth estimation (MDE) is the task of estimating depth from a single frame. This information is an essential knowledge in many computer vision tasks such as scene…

Similar Papers 제목 키워드 기반

Directional Smoothness and Gradient Methods: Convergence and Adaptivity

2024-03-06 · Aaron Mishkin, Ahmed Khaled, Yuanhao Wang, Aaron Defazio 외

We develop new sub-optimality bounds for gradient descent (GD) that depend on the conditioning of the objective along the path of optimization rather than on global, worst-case constants. Key to our proofs is directional…

A frequency-domain analysis of inexact gradient methods

2019-12-31 · Oran Gannot

We study robustness properties of some iterative gradient-based methods for strongly convex functions, as well as for the larger class of functions with sector-bounded gradients, under a relative error model. Proofs of t…

Learn and Verify: A Framework for Rigorous Verification of Physics-Informed Neural Networks

2026-01-27 · Kazuaki Tanaka, Kohei Yatabe arxiv

The numerical solution of differential equations using neural networks has become a central topic in scientific computing, with Physics-Informed Neural Networks (PINNs) emerging as a powerful paradigm for both forward an…

Adaptive Memory Crystallization for Autonomous AI Agent Learning in Dynamic Environments

2026-04-02 · Rajat Khanda, Mohammad Baqar, Sambuddha Chakrabarti, Satyasaran Changdar arxiv

Autonomous AI agents operating in dynamic environments face a persistent challenge: acquiring new capabilities without erasing prior knowledge. We present Adaptive Memory Crystallization (AMC), a memory architecture for …

Reinforcement Learning

Explicit option valuation in the exponential NIG model

2020-06-08 · Jean-Philippe Aguilar

We provide closed-form pricing formulas for a wide variety of path-independent options, in the exponential L\'evy model driven by the Normal inverse Gaussian process. The results are obtained in both the symmetric and as…

Formmodel