23 янв. 2024 г. · In this paper, we demonstrate that the inductive bias imposed on the by an equivariant model must also be taken into account when using latent representations.

In mathematics, equivariance is a form of symmetry for functions from one space with symmetry to another (such as symmetric spaces). Examples · Representation theory · Formalization

18 мар. 2024 г. · In this work, we propose to represent neural networks as computational graphs of parameters, which allows us to harness powerful graph neural networks and ...

Our general approach to equivariance is centered around the idea of representations, a prescription of how a group element acts on a given vector space.

3 февр. 2023 г. · This work introduces Allegro, a strictly local equivariant deep neural network interatomic potential architecture that simultaneously exhibits excellent ...

We propose new mechanisms for learning representations that are equivariant to both the agent's action, as well as symmetry transformations of the state-action ...

1 мая 2024 г. · This paper demonstrates the importance of considering the inductive bias imposed by an equivariant model when using latent representations as ...

Learning equivariant representations is a promising way to reduce sample and model complexity and improve the generalization performance of deep neural networks ...

Schur's lemma characterizes intertwiner spaces for irreducible representations linear equivariant maps between representations are called intertwiners on ...

Such equivariant structures yield a lower network capacity in terms of unknowns than alternatives like the Spatial Transformer [6] where a canonical ...