Sign in

Rob Cornish

@rob-cornish.bsky.social
16 followers 8 following 11 posts

Research fellow @ Oxford Statistics Department jrmcornish.github.io

PostsRepliesMedia
Rob Cornish @rob-cornish.bsky.social · 06/03/2025
You can also find an extended abstract of my longer Markov categories paper here: arxiv.org/abs/2412.09469
arxiv.org
Neural Network Symmetrisation in Concrete Settings
Cornish (2024) recently gave a general theory of neural network symmetrisation in the abstract context of Markov categories. We give a high-level overview of these results, and their concrete implicat...
000
Rob Cornish @rob-cornish.bsky.social · 06/03/2025
If this is of interest to you, here is a recent talk that @paolopmath.bsky.social and I gave for a class at MIT: www.youtube.com/watch?v=ozN4...
youtube.com
ACT4ED Special Lecture - Paolo Perrone, Rob Cornish (Oxford): Markov Categories, Symmetries, & GenAI
YouTube video by Zardini Lab
100
Rob Cornish @rob-cornish.bsky.social · 06/03/2025
This meta-strategy of using category theory to simplify complex reasoning appears useful much more generally, and I think the days of category theory for machine learning are just getting started.
100
Rob Cornish @rob-cornish.bsky.social · 06/03/2025
Using Markov categories, this earlier paper explained all previous work on symmetrisation as instances of a single common principle (sec 5 of arxiv.org/abs/2406.11814). It also extended this to methodology suited for *stochastic* models, which our ICLR paper applied to diffusions.
arxiv.org
Stochastic Neural Network Symmetrisation in Markov Categories
We consider the problem of symmetrising a neural network along a group homomorphism: given a homomorphism $φ: H \to G$, we would like a procedure that converts $H$-equivariant neural networks to $G$-e...
100
Rob Cornish @rob-cornish.bsky.social · 06/03/2025
The underlying theory we use here comes from arxiv.org/abs/2406.11814, which studied the problem of symmetrisation using *Markov categories*. Markov categories allow for reasoning about probability in a conceptual, diagrammatic way, while also maintaining full mathematical rigour.
arxiv.org
Stochastic Neural Network Symmetrisation in Markov Categories
We consider the problem of symmetrising a neural network along a group homomorphism: given a homomorphism $φ: H \to G$, we would like a procedure that converts $H$-equivariant neural networks to $G$-e...
100
Rob Cornish @rob-cornish.bsky.social · 06/03/2025
A meta-point of this paper is that category theory has utility for reasoning about current problems of interest in mainstream machine learning. The theory is predictive, not just descriptive. 🧵(1/6)
151
Rob Cornish @rob-cornish.bsky.social · 06/03/2025
You can also find an extended abstract of my longer Markov categories paper here: arxiv.org/abs/2412.09469
arxiv.org
Neural Network Symmetrisation in Concrete Settings
Cornish (2024) recently gave a general theory of neural network symmetrisation in the abstract context of Markov categories. We give a high-level overview of these results, and their concrete implicat...
000
Rob Cornish @rob-cornish.bsky.social · 06/03/2025
If this is of interest to you, here is a recent talk that @paolopmath.bsky.social and I gave for a class at MIT: www.youtube.com/watch?v=ozN4...
youtube.com
ACT4ED Special Lecture - Paolo Perrone, Rob Cornish (Oxford): Markov Categories, Symmetries, & GenAI
YouTube video by Zardini Lab
100
Rob Cornish @rob-cornish.bsky.social · 06/03/2025
This meta-strategy of using category theory to simplify complex reasoning appears useful much more generally, and I think the days of category theory for machine learning are just getting started.
100
Rob Cornish @rob-cornish.bsky.social · 06/03/2025
Using Markov categories, this earlier paper explained all previous work on symmetrisation as instances of a single common principle (sec 5 of arxiv.org/abs/2406.11814). It also extended this to methodology suited for *stochastic* models, which our ICLR paper applied to diffusions.
arxiv.org
Stochastic Neural Network Symmetrisation in Markov Categories
We consider the problem of symmetrising a neural network along a group homomorphism: given a homomorphism $φ: H \to G$, we would like a procedure that converts $H$-equivariant neural networks to $G$-e...
100
Rob Cornish @rob-cornish.bsky.social · 06/03/2025
The underlying theory we use here comes from arxiv.org/abs/2406.11814, which studied the problem of symmetrisation using *Markov categories*. Markov categories allow for reasoning about probability in a conceptual, diagrammatic way, while also maintaining full mathematical rigour.
100
Reposted by Rob Cornish
yeewhye.bsky.social @yeewhye.bsky.social · 04/03/2025
Awesome work by Kia @leoeleoleo1.bsky.social and @rob-cornish.bsky.social !
132