Pith. sign in

REVIEW 1 cited by

Why Quantization Improves Generalization: NTK of Binary Weight 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 2206.05916 v1 pith:VRF75R2S submitted 2022-06-13 cs.LG

classification cs.LG
keywords neuralnetworkbinarykernelweightnetworksquasiapproximate
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Quantized neural networks have drawn a lot of attention as they reduce the space and computational complexity during the inference. Moreover, there has been folklore that quantization acts as an implicit regularizer and thus can improve the generalizability of neural networks, yet no existing work formalizes this interesting folklore. In this paper, we take the binary weights in a neural network as random variables under stochastic rounding, and study the distribution propagation over different layers in the neural network. We propose a quasi neural network to approximate the distribution propagation, which is a neural network with continuous parameters and smooth activation function. We derive the neural tangent kernel (NTK) for this quasi neural network, and show that the eigenvalue of NTK decays at approximately exponential rate, which is comparable to that of Gaussian kernel with randomized scale. This in turn indicates that the Reproducing Kernel Hilbert Space (RKHS) of a binary weight neural network covers a strict subset of functions compared with the one with real value weights. We use experiments to verify that the quasi neural network we proposed can well approximate binary weight neural network. Furthermore, binary weight neural network gives a lower generalization gap compared with real value weight neural network, which is similar to the difference between Gaussian kernel and Laplace kernel.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 1 Pith paper

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

  1. Frequency Composition for Compressed and Domain-Adaptive Neural Networks

    cs.CV 2025-05 conditional novelty 6.0 of 10

    Training quantized models on low-frequency images plus frequency-aware batch normalization at test time improves both compression and domain-shift robustness.

Pith tools