Geometric Deep Learning: Grids, Groups, Graphs, Geodesics, and Gauges · HackerPapers discussions

Geometric Deep Learning: Grids, Groups, Graphs, Geodesics, and Gauges — HN submission

Mon, 08 Sep 2025 10:39:40 GMT

Geometric Deep Learning Grids, Groups, Graphs, Geodesics, and Gauges [pdf]

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

Geometric Deep Learning: Grids, Groups, Graphs, Geodesics, and Gauges — mentioned by r-bryan

Sun, 07 Sep 2025 02:23:48 GMT

Check out this 156-page tome: https://arxiv.org/abs/2104.13478: "Geometric Deep Learning: Grids, Groups, Graphs, Geodesics, and Gauges" The intro says that it "...serves a dual purpose: on one hand, it provides a common mathematical framework to study the most successful neural network architectures, such as CNNs, RNNs, GNNs, and Transformers. On the other hand, it gives a constructive procedure to incorporate prior physical knowledge into neural architectures and provide principled way to build future architectures yet to be invented." Working all the way through that, besides relearning a…

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

Geometric Deep Learning: Grids, Groups, Graphs, Geodesics, and Gauges — mentioned by smath

Wed, 18 Jun 2025 19:02:36 GMT

also relevant to 3d modeling of molecules using in drug discovering modeling -- and a subset of these authors have published along those lines more recently -- for e.g. https://arxiv.org/abs/2104.13478

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

Geometric Deep Learning: Grids, Groups, Graphs, Geodesics, and Gauges — HN submission

Thu, 31 Oct 2024 16:19:04 GMT

Geometric Deep Learning: Grids, Groups, Graphs, Geodesics, and Gauges

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

Geometric Deep Learning: Grids, Groups, Graphs, Geodesics, and Gauges — mentioned by PartiallyTyped

Sat, 11 Feb 2023 07:22:56 GMT

I am a big fan of “Geometric Deep Learning” and the view the authors propose. There is also a series of lectures. https://arxiv.org/abs/2104.13478

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

Geometric Deep Learning: Grids, Groups, Graphs, Geodesics, and Gauges — mentioned by 0xBABAD00C

Fri, 27 Jan 2023 17:54:47 GMT

+1 for probability via measure theory & functional analysis I would add the need for geometry and topology becoming more of a pre-requisite for picking up modern methods: https://arxiv.org/abs/2104.13478

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

Geometric Deep Learning: Grids, Groups, Graphs, Geodesics, and Gauges — mentioned by PartiallyTyped

Mon, 09 Jan 2023 18:10:05 GMT

I recommend against DL by Goodfellow. At this point it is pretty much outdated. Actually, anything specific to NNs is already outdated by release. You'd need the following background: - Linear Algebra - Multivariate Calculus - Probability theory && Statistics Then you need a decent ML book to get the foundations of ML, you can't go wrong with either of these: - Bishop's Pattern Recognition - Murphy's Probabilistic ML - Elements of statistical learning - Learning from data You can supplement Murphy's with the advanced book. Elements is a pretty tough book, consider going through "Introduction…

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

Geometric Deep Learning: Grids, Groups, Graphs, Geodesics, and Gauges — mentioned by PartiallyTyped

Sat, 30 Apr 2022 06:22:15 GMT

You may be interested in [1] where they go to a great extend to show that the convolution operation that we consider in DL is the dual of fourier series [2]. [1] https://geometricdeeplearning.com [2] https://arxiv.org/pdf/2104.13478.pdf page 27 (23 if you count book pages).

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

Geometric Deep Learning: Grids, Groups, Graphs, Geodesics, and Gauges — HN submission

Sat, 19 Feb 2022 09:10:06 GMT

Geometric Deep Learning: Grids, Groups, Graphs, Geodesics, and Gauges

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

Geometric Deep Learning: Grids, Groups, Graphs, Geodesics, and Gauges — mentioned by dplarson

Tue, 15 Jun 2021 15:49:59 GMT

Tweet with other links: https://twitter.com/mmbronstein/status/1404380398856060932 Paper (PDF): https://arxiv.org/pdf/2104.13478.pdf Blog post: https://towardsdatascience.com/geometric-foundations-of-deep...

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

Geometric Deep Learning: Grids, Groups, Graphs, Geodesics, and Gauges — mentioned by ArtWomb

Mon, 17 May 2021 11:52:51 GMT

Direct link to 156pp paper (an absolutely elegant read): Geometric Deep Learning: Grids, Groups, Graphs, Geodesics, and Gauges https://arxiv.org/abs/2104.13478 Stanford CS224W: Machine Learning with Graphs https://www.youtube.com/playlist?list=PLoROMvodv4rPLKxIpqhjh...

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

Geometric Deep Learning: Grids, Groups, Graphs, Geodesics, and Gauges — HN submission

Thu, 13 May 2021 20:00:26 GMT

Geometric Deep Learning: Grids, Groups, Graphs, Geodesics, and Gauges

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

Geometric Deep Learning: Grids, Groups, Graphs, Geodesics, and Gauges — HN submission

Thu, 29 Apr 2021 10:43:44 GMT

Geometric Deep Learning: Grids, Groups, Graphs, Geodesics, and Gauges

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