Pith. sign in

REVIEW 13 cited by

Robust Learning with Jacobian Regularization

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 1908.02729 v1 pith:LWSR7EID submitted 2019-08-07 stat.ML cs.LG

Judy Hoffman , Daniel A. Roberts , Sho Yaida This is my paper · ORCID
classification stat.MLcs.LG
keywords inputjacobiandataguaranteelearningperturbationsregularizationrobustness
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Design of reliable systems must guarantee stability against input perturbations. In machine learning, such guarantee entails preventing overfitting and ensuring robustness of models against corruption of input data. In order to maximize stability, we analyze and develop a computationally efficient implementation of Jacobian regularization that increases classification margins of neural networks. The stabilizing effect of the Jacobian regularizer leads to significant improvements in robustness, as measured against both random and adversarial input perturbations, without severely degrading generalization properties on clean data.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 13 Pith papers

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

  1. An Adjoint-Sensitivity Framework for Lost-in-the-Middle Phenomena in Causal Residual Transformers

    stat.ML 2026-07 conditional novelty 6.0 of 10

    A new adjoint-sensitivity analysis shows that a normalized influence density evolves exactly along gradient flow and that primacy, recency, and lost-in-the-middle arise from distinct channels under checkable conditions.

  2. Beyond Objective Expressivity: Geometry Preservation in Multimodal Contrastive Learning

    cs.LG 2026-07 conditional novelty 6.0 of 10

    Well-conditioned encoder Jacobians, achieved via residual paths and LeakyReLU activations, improve trimodal contrastive learning retrieval and linear-probe performance across objectives and datasets.

  3. On Adversarial Vulnerability of Vision-Language Models through the Lens of Intermediate Spectral Subspaces

    cs.LG 2026-07 conditional novelty 6.0 of 10

    Aligning adversarial perturbations with the near-null singular directions of intermediate linear layers in transformer VLMs yields stronger attacks than existing feature- and output-space methods.

  4. Semantic Causality-Aware Vision-Based 3D Occupancy Prediction

    cs.CV 2025-09 conditional novelty 6.0 of 10

    A class-conditional gradient loss (Causal Loss) plus channel-grouped lifting, learnable camera offsets, and normalized convolution raises Occ3D mIoU by 1.2/0.8 points and cuts the camera-noise mIoU drop from 32% to 7%.

  5. Improving Data and Parameter Efficiency of Neural Language Models Using Representation Analysis

    cs.CL 2025-07 conditional novelty 6.0 of 10

    Representation smoothness can be used to regularize training, stop early without validation labels, and guide active learning combined with parameter-efficient fine-tuning, reducing data and compute.

  6. Loss Landscape Analysis for Reliable Quantized ML Models for Scientific Sensing

    cs.LG 2025-02 conditional novelty 6.0 of 10

    Loss landscape flatness and connectivity visually correlate with robustness to noise and bit flips in two quantized scientific sensing models, but the correlation is not quantified and the a priori claim remains unvalidated.

  7. Interleaved Noise Injection Improves Clean, Corrupted, and OOD Performance

    cs.LG 2026-07 conditional novelty 5.0 of 10

    Interleaving clean and noisy training epochs improves clean, corrupted, and out-of-distribution accuracy on CIFAR-100 and ImageNet for CNNs and ViTs, with impulse noise best for ResNets and Gaussian noise best for ViTs.

  8. Modular Foundation Models for Time-Series Perception in Digital Twins

    cs.LG 2026-07 conditional novelty 5.0 of 10

    A gated bank of frozen self-supervised time-series encoders, aligned and aggregated by a Transformer, supports competitive multi-task perception for digital twins and hydro-generator virtual sensing.

  9. Distance-informed Neural Processes

    cs.LG 2025-08 conditional novelty 5.0 of 10

    A neural process with a bi-Lipschitz-regularized local encoder achieves better uncertainty calibration and OOD detection than existing NP variants.

  10. GrokAlign: Geometric Characterisation and Acceleration of Grokking

    cs.LG 2025-06 conditional novelty 5.0 of 10

    GrokAlign, a Jacobian-norm regularizer, accelerates grokking by aligning Jacobians with training data, and centroid alignment tracks when generalization and robustness emerge.

  11. Geometric flow regularization in latent spaces for smooth dynamics with the efficient variations of curvature

    math.NA 2025-06 conditional novelty 5.0 of 10

    Curvature-flow-regularized latent spaces improve mean out-of-distribution errors for Burger's equation relative to a plain autoencoder, but the flows are heuristic and the evidence is limited.

  12. Hidden Representation Clustering with Multi-Task Representation Learning towards Robust Online Budget Allocation

    cs.LG 2025-06 conditional novelty 5.0 of 10

    Budget allocation by clustering users in a learned hidden representation space and optimizing per cluster improves order volume and gross merchandise volume by up to 0.65% relative to individual-level baselines in Mei...

  13. A Bayesian Framework for Regularized Estimation in Multivariate Models Integrating Approximate Computing Concepts

    stat.ME 2025-09 reject novelty 3.0 of 10

    The paper shows that adding Gaussian noise to a parameter is equivalent to inflating its prior variance, and uses this to claim a Bayesian interpretation of quantization and to justify shrinkage in regularized LDA.

Pith tools