TE
TechEcho
Home24h TopNewestBestAskShowJobs
GitHubTwitter
Home

TechEcho

A tech news platform built with Next.js, providing global tech news and discussions.

GitHubTwitter

Home

HomeNewestBestAskShowJobs

Resources

HackerNews APIOriginal HackerNewsNext.js

© 2025 TechEcho. All rights reserved.

Data diversity: Preserving variety in data sets should aid machine learning

50 pointsby upenover 8 years ago

3 comments

rokosbasiliskover 8 years ago
I believe they are using mcmcs at the core. markov chain multi carlos. this might be useful if you are wondering what it is <a href="http:&#x2F;&#x2F;mlwhiz.com&#x2F;blog&#x2F;2015&#x2F;08&#x2F;19&#x2F;MCMC_Algorithms_Beta_Distribution&#x2F;" rel="nofollow">http:&#x2F;&#x2F;mlwhiz.com&#x2F;blog&#x2F;2015&#x2F;08&#x2F;19&#x2F;MCMC_Algorithms_Beta_Distr...</a>
q_revertover 8 years ago
I think this is the paper, which oddly isn&#x27;t linked in the article:<p><a href="https:&#x2F;&#x2F;arxiv.org&#x2F;abs&#x2F;1509.01618" rel="nofollow">https:&#x2F;&#x2F;arxiv.org&#x2F;abs&#x2F;1509.01618</a>
评论 #13207751 未加载
评论 #13208038 未加载
opaqeover 8 years ago
Is there a more detailed paper describing the algorithm? The description is very vague in the article. When they pick the two points, is there an evaluation on how much &quot;diversity&quot; increases w&#x2F;r&#x2F;t each of the three possible operations, and that&#x27;s how they choose?<p>edit: thanks @q_revert for linking the paper