Pith. sign in

REVIEW 2 cited by

Better Training using Weight-Constrained Stochastic Dynamics

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 2106.10704 v1 pith:NLZYDC3N submitted 2021-06-20 cs.LG stat.ML

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

We employ constraints to control the parameter space of deep neural networks throughout training. The use of customized, appropriately designed constraints can reduce the vanishing/exploding gradients problem, improve smoothness of classification boundaries, control weight magnitudes and stabilize deep neural networks, and thus enhance the robustness of training algorithms and the generalization capabilities of neural networks. We provide a general approach to efficiently incorporate constraints into a stochastic gradient Langevin framework, allowing enhanced exploration of the loss landscape. We also present specific examples of constrained training methods motivated by orthogonality preservation for weight matrices and explicit weight normalizations. Discretization schemes are provided both for the overdamped formulation of Langevin dynamics and the underdamped form, in which momenta further improve sampling efficiency. These optimization schemes can be used directly, without needing to adapt neural network architecture design choices or to modify the objective with regularization terms, and see performance improvements in classification tasks.

Discussion (0). Sign in to comment.

Forward citations

Cited by 2 Pith papers

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

  1. Brownian dynamics with soft constraints in soft matter systems

    cond-mat.soft 2026-01 conditional novelty 6.0 of 10

    Softly constrained Brownian dynamics are derived by singular perturbation theory, with a new 'project-then-average' mobility rule for rapidly varying mobility.

  2. Recursive Bound-Constrained AdaGrad with Applications to Multilevel and Domain Decomposition Minimization

    math.OC 2025-07 conditional novelty 6.0 of 10

    Two noise-tolerant, bound-constrained AdaGrad variants for multilevel and domain-decomposition problems are proved to find an epsilon-approximate critical point in O(epsilon^-2) iterations with high probability.

Pith tools