https://sublinear.info/index.php?action=history&feed=atom&title=Open_Problems_talk%3A85Open Problems talk:85 - Revision history2026-04-22T21:48:46ZRevision history for this page on the wikiMediaWiki 1.31.10https://sublinear.info/index.php?title=Open_Problems_talk:85&diff=1319&oldid=prevJakub Tětek: adding a reference2021-04-12T08:55:18Z<p>adding a reference</p>
<p><b>New page</b></p><div>There came out a paper [1] that considers a very similar question. It does not solve this question explicitly but it would be worth looking at whether their methods imply a solution to this problem. At the very least, it is very relevant.<br />
<br />
[1] Sample Amplification:Increasing Dataset Size even when Learning is Impossible; Brian Axelrod, Shivam Garg, Vatsal Sharan, Gregory Valiant; http://proceedings.mlr.press/v119/axelrod20a/axelrod20a.pdf</div>Jakub Tětek