Demonstration of Decentralized, Physics-Driven Learning · HackerPapers discussions

Demonstration of Decentralized, Physics-Driven Learning — HN submission

Thu, 02 Jun 2022 07:38:09 GMT

Demonstration of Decentralized, Physics-Driven Learning

1 point; 0 discussion replies on HN. Paper and source history. A submission is not an endorsement.

Demonstration of Decentralized, Physics-Driven Learning — mentioned by YeGoblynQueenne

Wed, 23 Mar 2022 18:27:53 GMT

You are right of course that it shouldn't, but in practice it always is. The pragmatic reason for that is that if a team spends a month and a few thousand dollars developing and tuning a system, and then they find that the first time they test it on their held-out test set it doesn't work, there is no way that they'll just drop it and accept that all their effort and funds got to waste. They'll just keep trying until their system retruns the best results on the test set. At which point they've overfitted their system to the test set. It's rare that this is described as clearly as in the paper…

Paper and discussion history. A mention is not an endorsement.

Demonstration of Decentralized, Physics-Driven Learning — mentioned by mlajtos

Tue, 22 Mar 2022 15:37:27 GMT

Link to arXiv: https://arxiv.org/abs/2108.00275

Paper and discussion history. A mention is not an endorsement.

Demonstration of Decentralized, Physics-Driven Learning — mentioned by RaisinLoaf69

Tue, 22 Mar 2022 15:34:45 GMT

I actually work on this project! Feel free to ask any questions. Also, here’s an arxiv link to one of the papers if anyone is interested: https://arxiv.org/abs/2108.00275

Paper and discussion history. A mention is not an endorsement.