Pith. sign in

REVIEW 7 cited by

Expressivity and Approximation Properties of Deep Neural Networks with ReLU$^k$ Activation

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 2312.16483 v2 pith:37VL664E submitted 2023-12-27 cs.LG cs.NAcs.NEmath.NA

classification cs.LGcs.NAcs.NEmath.NA
keywords networksreludeepfunctionsactivationapproximationspacesapproximate
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
abstract

In this paper, we investigate the expressivity and approximation properties of deep neural networks employing the ReLU$^k$ activation function for $k \geq 2$. Although deep ReLU networks can approximate polynomials effectively, deep ReLU$^k$ networks have the capability to represent higher-degree polynomials precisely. Our initial contribution is a comprehensive, constructive proof for polynomial representation using deep ReLU$^k$ networks. This allows us to establish an upper bound on both the size and count of network parameters. Consequently, we are able to demonstrate a suboptimal approximation rate for functions from Sobolev spaces as well as for analytic functions. Additionally, through an exploration of the representation power of deep ReLU$^k$ networks for shallow networks, we reveal that deep ReLU$^k$ networks can approximate functions from a range of variation spaces, extending beyond those generated solely by the ReLU$^k$ activation function. This finding demonstrates the adaptability of deep ReLU$^k$ networks in approximating functions within various variation spaces.

Discussion (0). Sign in to comment.

Forward citations

Cited by 7 Pith papers

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

  1. Neural Flow Operators can Approximate any Operator: Abstract Frameworks and Universal Approximations

    cs.LG 2026-05 unverdicted novelty 8.0 of 10

    An abstract framework for neural flows with composition and separation structures is proven to universally approximate any operator, recovering ResNet and plain architectures via discretization.

  2. Neural Flow Operators can Approximate any Operator: Abstract Frameworks and Universal Approximations

    cs.LG 2026-05 unverdicted novelty 7.0 of 10

    Neural flow operators with composition and separation structures are proven to universally approximate any operator in finite and infinite dimensions, recovering ResNet-type and plain architectures via time discretizations.

  3. Shallow ReLU$^s$ Networks in $L^p$-Type and Sobolev Spaces: Approximation and Path-Norm Controlled Generalization

    stat.ML 2026-05 unverdicted novelty 7.0 of 10

    Shallow ReLU^s networks achieve specific improved approximation rates in L^p spaces and minimax-optimal generalization in nonparametric regression over Barron and Sobolev spaces with path-norm control.

  4. Shallow ReLU$^s$ Networks in $L^p$-Type and Sobolev Spaces: Approximation and Path-Norm Controlled Generalization

    stat.ML 2026-05 unverdicted novelty 6.0 of 10

    Shallow ReLU^s networks achieve improved approximation rates in L^p spaces for p below a dimension-dependent threshold and minimax-optimal generalization bounds in Barron and Sobolev spaces under l1 path-norm control.

  5. Shallow ReLU$^s$ Networks in $L^p$-Type and Sobolev Spaces: Approximation and Path-Norm Controlled Generalization

    stat.ML 2026-05 unverdicted novelty 5.0 of 10

    Derives approximation bounds for shallow ReLU^s networks in L^p and Sobolev spaces and shows path-norm regularized networks achieve minimax optimal generalization rates in regression.

  6. Shallow ReLU$^s$ Networks in $L^p$-Type and Sobolev Spaces: Approximation and Path-Norm Controlled Generalization

    stat.ML 2026-05 unverdicted novelty 5.0 of 10

    Derives explicit approximation rates for shallow ReLU^s networks in L^p and Sobolev spaces and shows path-norm regularized networks achieve minimax-optimal generalization rates with matching lower bounds.

  7. Digital Twin Channel-Aided CSI Prediction: An Environment-Based Subspace Extraction Approach for Achieving Low Overhead and High Robustness

    eess.SP 2025-08 unverdicted novelty 5.0 of 10

    Using a digital-twin-derived channel subspace basis as a prior, the method predicts full spatial-frequency CSI from partial pilots, claiming up to 50% pilot overhead reduction and one-coherence-time-ahead prediction i...

Pith tools