Symmetry in Neural Network Parameter Spaces — mentioned by fc417fc802

Fri, 09 Jan 2026 15:10:58 GMT

Note that I'm not great at math so it's possible I've entirely misunderstood you. Here's an example of directly leveraging a transform to optimize the training process. ( https://arxiv.org/abs/2410.21265 ) And here are two examples that apply geometry to neural nets more generally. ( https://arxiv.org/abs/2506.13018 ) ( https://arxiv.org/abs/2309.16512 )

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

Symmetry in Neural Network Parameter Spaces — mentioned by observationist

Tue, 06 Jan 2026 00:13:25 GMT

Neural networks are effectively gauge invariant, and you have a huge space of valid isomorphisms as far as possible "valid" layer orderings go, and if your network is overparameterized, the space of "good enough" approximations gets correspondingly larger. The good enough sets are a sort of fuzzy gauge quotient approximating some "ideal" function per layer or cluster or block (depending on your optimizer and architecture.) https://arxiv.org/html/2506.13018v2 - Here's an interesting paper that can help inform how you might look at networks, especially in the context of lottery tickets, gauge…

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

Symmetry in Neural Network Parameter Spaces · HackerPapers discussions

Symmetry in Neural Network Parameter Spaces — mentioned by fc417fc802

Symmetry in Neural Network Parameter Spaces — mentioned by observationist