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.

Private Multi-Party Machine Learning

22 pointsby alex_hirnerover 8 years ago

2 comments

webmavenover 8 years ago
Slides from the scheduled presentations[0], as well as most of the accepted papers[1], are available.<p>This is some seriously mind-bending stuff. Google is represented by a couple of papers, but I was really hoping that the privacy-preserving techniques they used in training the network for Inbox Smart Replies would be explained. No such luck.<p>[0] <a href="https:&#x2F;&#x2F;pmpml.github.io&#x2F;PMPML16&#x2F;#schedule" rel="nofollow">https:&#x2F;&#x2F;pmpml.github.io&#x2F;PMPML16&#x2F;#schedule</a><p>[1] <a href="https:&#x2F;&#x2F;pmpml.github.io&#x2F;PMPML16&#x2F;#papers" rel="nofollow">https:&#x2F;&#x2F;pmpml.github.io&#x2F;PMPML16&#x2F;#papers</a>
jhoechtlover 8 years ago
I wonder why nobody of these guys has been there <a href="http:&#x2F;&#x2F;www.enigma.co" rel="nofollow">http:&#x2F;&#x2F;www.enigma.co</a>