REVIEW 3 cited by
Universal approximations of permutation invariant/equivariant functions by deep neural networks
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
abstract
In this paper, we develop a theory about the relationship between $G$-invariant/equivariant functions and deep neural networks for finite group $G$. Especially, for a given $G$-invariant/equivariant function, we construct its universal approximator by deep neural network whose layers equip $G$-actions and each affine transformations are $G$-equivariant/invariant. Due to representation theory, we can show that this approximator has exponentially fewer free parameters than usual models.
Forward citations
Cited by 3 Pith papers
-
On the Dimension-Free Approximation of Deep Neural Networks for Symmetric Korobov Functions
Symmetric squared-ReLU networks approximate symmetric Korobov functions at rate O(m^{-1}) with a dimension-independent prefactor, and gradient-based learning achieves M^{-2/3} generalization error.
-
When Attention is Beneficial for Learning Wireless Resource Allocation Efficiently?
Attention appears in a learned wireless policy only along the dimension with interference when that interference is not already present in the environmental parameters.
-
Transformers Are Universally Consistent
HyT, a hyperbolic Transformer, is claimed to be universally consistent for L2 regression, but the proof is invalidated by an algebraic error and circular reasoning.
Discussion (0). Sign in to comment.