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。

Differentiating SSA-Form Programs in Julia (2018) [pdf]

87 点作者 idiliv超过 6 年前

3 条评论

cs702超过 6 年前
As the author explains, this approach to automatic differentiation (AD) via transformation of source code &quot;supports control flow, higher-order functions and nested derivatives. The differentiated code can be further fed into a traditional compiler such as LLVM, which results in an extremely efficient derivative program. Further, it opens up the opportunity for robust traditional compiler techniques to be extended to machine learning, enabling kernel fusion or compilation for accelerators with no artificial limitations on the kinds of models that researchers can express. This combination has not previously been possible in a high-level, general-purpose programming language.&quot;<p>The author&#x27;s package, Zygote, makes <i>all</i> Julia code differentiable, so <i>any program</i> can be optimized as an ML&#x2F;AI model to learn a set of parameters given some training objective.[a]<p>:-)<p>[a] That said, you will not be able magically to overcome the limits of mathematics, in case you&#x27;re wondering. See darawk&#x27;s and b_tterc_p&#x27;s comments below.
评论 #19119966 未加载
评论 #19120122 未加载
评论 #19121822 未加载
KenoFischer超过 6 年前
Hi folks, this is part of of larger effort in the Julia community to do a ground up re-think of infrastructure for machine learning. You can find an overview of the entire effort in our recent blog post [1]. Happy to answer questions.<p>[1] <a href="https:&#x2F;&#x2F;julialang.org&#x2F;blog&#x2F;2018&#x2F;12&#x2F;ml-language-compiler" rel="nofollow">https:&#x2F;&#x2F;julialang.org&#x2F;blog&#x2F;2018&#x2F;12&#x2F;ml-language-compiler</a>
评论 #19120202 未加载
infogulch超过 6 年前
Is this related to previous discussion The Simple Essence of Automatic Differentiation [1]?<p>[1]: <a href="https:&#x2F;&#x2F;news.ycombinator.com&#x2F;item?id=18306860" rel="nofollow">https:&#x2F;&#x2F;news.ycombinator.com&#x2F;item?id=18306860</a>