Pith. sign in

REVIEW 3 cited by

Lipschitz Recurrent 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 2006.12070 v3 pith:OS3K4GCJ submitted 2020-06-22 cs.LG math.DSstat.ML

classification cs.LGmath.DSstat.ML
keywords recurrentlipschitzunitanalysiscontinuous-timedemonstratenetworksneural
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Viewing recurrent neural networks (RNNs) as continuous-time dynamical systems, we propose a recurrent unit that describes the hidden state's evolution with two parts: a well-understood linear component plus a Lipschitz nonlinearity. This particular functional form facilitates stability analysis of the long-term behavior of the recurrent unit using tools from nonlinear systems theory. In turn, this enables architectural design decisions before experimentation. Sufficient conditions for global stability of the recurrent unit are obtained, motivating a novel scheme for constructing hidden-to-hidden matrices. Our experiments demonstrate that the Lipschitz RNN can outperform existing recurrent units on a range of benchmark tasks, including computer vision, language modeling and speech prediction tasks. Finally, through Hessian-based analysis we demonstrate that our Lipschitz recurrent unit is more robust with respect to input and parameter perturbations as compared to other continuous-time RNNs.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 3 Pith papers

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

  1. Temporal horizons in forecasting: a performance-learnability trade-off

    cs.LG 2025-06 conditional novelty 5.0 of 10

    Longer training horizons improve forecast quality but worsen learnability, with loss-landscape roughness growing exponentially for chaotic dynamics and linearly for limit cycles.

  2. Deep Loss Convexification for Learning Iterative Models

    cs.CV 2024-11 conditional novelty 5.0 of 10

    Adding star-convexity hinge losses during training makes a model's loss landscape bowl-shaped around the ground truth and improves iterative predictions on RNN, point cloud registration, and image alignment tasks.

  3. The Good, The Efficient and the Inductive Biases: Exploring Efficiency in Deep Learning Through the Use of Inductive Biases

    cs.LG 2024-11 conditional novelty 3.0 of 10

    A dissertation synthesizing the author's papers on continuous kernel convolutions and symmetry-preserving architectures, claiming these inductive biases improve deep learning efficiency.

Pith tools