Pith. sign in

REVIEW 3 cited by

Local Lipschitz Bounds of Deep Neural Networks

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

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 2004.13135 v3 pith:MYP2RJIE submitted 2020-04-27 stat.ML cs.LGq-fin.MF

Calypso Herrera , Florian Krach , Josef Teichmann This is my paper
classification stat.MLcs.LGq-fin.MF
keywords lipschitzconstantsneuralboundsnetworksoptimizationconstantconvergence
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

The Lipschitz constant is an important quantity that arises in analysing the convergence of gradient-based optimization methods. It is generally unclear how to estimate the Lipschitz constant of a complex model. Thus, this paper studies an important problem that may be useful to the broader area of non-convex optimization. The main result provides a local upper bound on the Lipschitz constants of a multi-layer feed-forward neural network and its gradient. Moreover, lower bounds are established as well, which are used to show that it is impossible to derive global upper bounds for the Lipschitz constants. In contrast to previous works, we compute the Lipschitz constants with respect to the network parameters and not with respect to the inputs. These constants are needed for the theoretical description of many step size schedulers of gradient based optimization schemes and their convergence analysis. The idea is both simple and effective. The results are extended to a generalization of neural networks, continuously deep neural networks, which are described by controlled ODEs.

Discussion (0). Sign in to comment.

Forward citations

Cited by 3 Pith papers

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

  1. Pointwise Generalization in Deep Neural Networks

    cs.LG 2026-05 unverdicted novelty 7.0 of 10

    Proposes pointwise Riemannian Dimension from feature eigenvalues to derive tighter, representation-aware generalization bounds for deep networks in the nonlinear regime.

  2. Operator Neural Jump ODEs: $L^2$-optimal prediction in function spaces

    stat.ML 2026-07 conditional novelty 6.0 of 10

    Operator Neural Jump ODEs provably converge, in the training loss and in the observation metric d_k, to the conditional expectation of L2(Ξ)-valued stochastic processes observed at random times and spatial points.

  3. Fine-Tuning Without Forgetting via Loss-Adaptive Learning Rates

    cs.LG 2026-05 unverdicted novelty 5.0 of 10

    FINCH is a loss-adaptive learning-rate schedule that reduces forgetting by 93% on average during LLM fine-tuning while matching standard task performance across several benchmarks.

Pith tools