Pith. sign in

REVIEW 2 cited by

Rational 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

arxiv 2004.01902 v2 pith:PFGNLMGQ submitted 2020-04-04 cs.NE cs.LGcs.NAmath.NAstat.ML

Rational neural networks

classification cs.NE cs.LGcs.NAmath.NAstat.ML
keywords networksneuralrationalactivationfunctionsnetworkrelualternative
verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved
0 comments
read the original abstract

We consider neural networks with rational activation functions. The choice of the nonlinear activation function in deep learning architectures is crucial and heavily impacts the performance of a neural network. We establish optimal bounds in terms of network complexity and prove that rational neural networks approximate smooth functions more efficiently than ReLU networks with exponentially smaller depth. The flexibility and smoothness of rational activation functions make them an attractive alternative to ReLU, as we demonstrate with numerical experiments.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 2 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. Copositive Matrices with Ordered Off-Diagonal Entries

    math.OC 2026-05 unverdicted novelty 7.0

    Copositive matrices with nondecreasing off-diagonal entries admit a PSD plus nonnegative decomposition, which implies exactness of a natural relaxation for separable quadratic optimization over the simplex.

  2. FlexAct: Why Learn when you can Pick?

    cs.LG 2026-01 reject novelty 2.0

    A Gumbel-Softmax router that discretely selects among five fixed activation functions, plus a gradient-norm regularizer, recovers the generating activation on toy regression tasks but never beats the matching fixed ac...