Pith. sign in

REVIEW

Volumization as a Natural Generalization of Weight Decay

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 2003.11243 v2 pith:RLPUDBVM submitted 2020-03-25 cs.LG stat.ML

classification cs.LGstat.ML
keywords methodweightnetworksneuraldecayregularizationvolumizationgeneralization
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
abstract

We propose a novel regularization method, called \textit{volumization}, for neural networks. Inspired by physics, we define a physical volume for the weight parameters in neural networks, and we show that this method is an effective way of regularizing neural networks. Intuitively, this method interpolates between an $L_2$ and $L_\infty$ regularization. Therefore, weight decay and weight clipping become special cases of the proposed algorithm. We prove, on a toy example, that the essence of this method is a regularization technique to control bias-variance tradeoff. The method is shown to do well in the categories where the standard weight decay method is shown to work well, including improving the generalization of networks and preventing memorization. Moreover, we show that the volumization might lead to a simple method for training a neural network whose weight is binary or ternary.

Discussion (0). Continue with ORCID to comment.

Pith tools