TE
科技回声
首页24小时热榜最新最佳问答展示工作
GitHubTwitter
首页

科技回声

基于 Next.js 构建的科技新闻平台,提供全球科技新闻和讨论内容。

GitHubTwitter

首页

首页最新最佳问答展示工作

资源链接

HackerNews API原版 HackerNewsNext.js

© 2025 科技回声. 版权所有。

Tackling the curse of dimensionality with physics-informed neural networks

77 点作者 jhoho超过 1 年前

2 条评论

SeanAnderson超过 1 年前
&gt; For instance, we solve nontrivial nonlinear PDEs (one HJB equation and one Black-Scholes equation) in 100,000 dimensions in 6 hours on a single GPU using SDGD with PINNs<p>100,000 dimensions? I thought there were like... 11 tops? <a href="https:&#x2F;&#x2F;imagine.gsfc.nasa.gov&#x2F;science&#x2F;questions&#x2F;superstring.html#:~:text=The%20only%20consistent%20framework%20to%20describe%20those%20strings%20implies%20a%2010%2D%20or%20even%20conceivably%20an%2011%2Ddimension%20world" rel="nofollow noreferrer">https:&#x2F;&#x2F;imagine.gsfc.nasa.gov&#x2F;science&#x2F;questions&#x2F;superstring....</a><p>(edit: oops, I misunderstood the context of dimensions here. my bad. thanks)
评论 #37565605 未加载
评论 #37565611 未加载
评论 #37569617 未加载
Eliezer超过 1 年前
Iiii do not think you should be able to solve the Schrodinger equation with thousands of dimensions in general on a non-quantum computer, what with that being a quantum-mechanical equation some of whose solutions would reflect quantum-hard problems?
评论 #37567283 未加载
评论 #37569912 未加载