AI Feynman: a Physics-Inspired Method for Symbolic Regression · HackerPapers discussions

AI Feynman: a Physics-Inspired Method for Symbolic Regression — mentioned by yorwba

Mon, 13 Apr 2026 12:56:06 GMT

Yes, metamath uses a large collection of specialized but reusable building blocks, so it doesn't blow up exponentially. However, if you want to "just do gradient descent" on general trees built from a single universal primitive, you now have to rediscover all those building blocks on the fly. And while the final result may have a compact representation as a DAG by merging common subexpressions, you also need to be able to represent potential alternative solutions, and that's where the exponential blowup comes in. Or you could accept that there's already a large collection of known useful…

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

AI Feynman: a Physics-Inspired Method for Symbolic Regression — HN submission

Mon, 10 Nov 2025 22:17:05 GMT

AI Feynman: A Physics-Inspired Method for Symbolic Regression

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

AI Feynman: a Physics-Inspired Method for Symbolic Regression — mentioned by ben_w

Fri, 03 Jun 2022 16:55:09 GMT

Indeed: • https://news.ycombinator.com/item?id=31609839 • https://arxiv.org/pdf/1810.10525.pdf • https://arxiv.org/pdf/1905.11481.pdf

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

AI Feynman: a Physics-Inspired Method for Symbolic Regression — HN submission

Sat, 08 Jan 2022 14:15:11 GMT

AI Feynman: A Physics-Inspired Method for Symbolic Regression

6 points; 1 discussion reply on HN. Paper and source history. A submission is not an endorsement.

AI Feynman: a Physics-Inspired Method for Symbolic Regression — HN submission

Wed, 27 Jan 2021 21:23:56 GMT

AI Feynman: A Physics-Inspired Method for Symbolic Regression

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

AI Feynman: a Physics-Inspired Method for Symbolic Regression — mentioned by knzhou

Sat, 23 Nov 2019 00:17:46 GMT

This is exactly it. Earlier this year there was a hyped up paper [0] going around claiming that they could derive physics with AI. On inspection I found that what they actually did was this: 1. Take one simple physics equation, such as F = ma 2. Generate 10^6 tuples exactly satisfying this equation (F = 6, m = 2, a = 3), with absolutely no redundant, erroneous, or extraneous information 3. Feed these to a primitive "AI" system which brute-force tries the simplest relations that could relate the three provided variables (m = Fa, a = Fm, F = ma, ...) 4. Recover F = ma, declare physicists…

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

AI Feynman: a Physics-Inspired Method for Symbolic Regression — HN submission

Fri, 31 May 2019 00:30:10 GMT

AI Feynman: A Physics-Inspired Method for Symbolic Regression

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