[1707.02568] Solving high-dimensional partial differential equations using deep learningcontact arXivarXiv Twitter

Developing algorithms for solving high-dimensional partial differential equations (PDEs) has been an exceedingly difficult task for a long time, due to the notoriously difficult problem known as the "curse of dimensionality". This paper introduces a deep learning-based approach that can handle general high-dimensional parabolic PDEs. To this end, the PDEs are reformulated using backward stochastic differential equations and the gradient of the unknown solution is approximated by neural networks, very much in the spirit of deep reinforcement learning with the gradient acting as the policy function. Numerical results on examples including the nonlinear Black-Scholes equation, the Hamilton-Jacobi-Bellman equation, and the Allen-Cahn equation suggest that the proposed algorithm is quite effective in high dimensions, in terms of both accuracy and cost. This opens up new possibilities in economics, finance, operational research, and physics, by considering all participating agents, assets, r

1 mentions: @makolooon
Keywords: deep learning
Date: 2020/02/23 11:20

Referring Tweets

@makolooon Let's solve 高次元偏微分方程式 with Deep Learningのお気持ち論文 t.co/BQNlBUA1pM

Related Entries

Read more {rBayesianOptimization}パッケージによるベイズ最適化で機械学習パラメータチューニングをお手軽に - 六本木で働くデータサイエンティストのブログ
0 users, 0 mentions 2018/04/22 03:40
Read more practical-pytorch/reinforce-gridworld.ipynb at master · spro/practical-pytorch · GitHub
0 users, 0 mentions 2018/04/22 03:40
Read more 特許公報を用いた自然言語処理による業界分析、及びSpotfireによる可視化 統合TV(togotv)|生命科学系DB・ツール使い倒し系チャンネル
0 users, 0 mentions 2018/04/22 03:40
Read more [1909.09428] A Critical Analysis of Biased Parsers in Unsupervised Parsing
0 users, 1 mentions 2019/09/23 11:18
Read more GitHub - codelibs/elasticsearch-vector: Vector type and search functions for Elasticsearch
0 users, 0 mentions 2020/05/10 08:21