Pith. sign in

REVIEW 8 cited by

A Universal Law of Robustness via Isoperimetry

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 2105.12806 v4 pith:OUP3553C submitted 2021-05-26 cs.LG stat.ML

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

Classically, data interpolation with a parametrized model class is possible as long as the number of parameters is larger than the number of equations to be satisfied. A puzzling phenomenon in deep learning is that models are trained with many more parameters than what this classical theory would suggest. We propose a partial theoretical explanation for this phenomenon. We prove that for a broad class of data distributions and model classes, overparametrization is necessary if one wants to interpolate the data smoothly. Namely we show that smooth interpolation requires $d$ times more parameters than mere interpolation, where $d$ is the ambient data dimension. We prove this universal law of robustness for any smoothly parametrized function class with polynomial size weights, and any covariate distribution verifying isoperimetry. In the case of two-layers neural networks and Gaussian covariates, this law was conjectured in prior work by Bubeck, Li and Nagaraj. We also give an interpretation of our result as an improved generalization bound for model classes consisting of smooth functions.

Discussion (0). Sign in to comment.

Forward citations

Cited by 8 Pith papers

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

  1. A law of robustness for two-layer neural networks with arbitrary weights

    cs.LG 2026-07 accept novelty 8.0 of 10

    Any width-m two-layer piecewise-linear network with arbitrary weights that fits n noisy labels below the noise floor has Lip ≳ ε sqrt(n/(m log(m n d/ε))) with high probability on the sphere or Gaussian.

  2. LOSCAR-SGD: Local SGD with Communication-Computation Overlap and Delay-Corrected Sparse Model Averaging

    cs.LG 2026-05 unverdicted novelty 7.0 of 10

    LOSCAR-SGD combines local updates, sparse model averaging, and communication-computation overlap with a delay-corrected merge rule, providing convergence rates for smooth non-convex objectives under worker heterogeneity.

  3. Ringmaster LMO: Asynchronous Linear Minimization Oracle Momentum Method

    cs.LG 2026-05 unverdicted novelty 7.0 of 10

    Ringmaster LMO extends delay-thresholding from ASGD to LMO-based momentum updates, providing convergence guarantees under (L0, L1)-smoothness and time-complexity bounds that recover optimal rates in the Euclidean case.

  4. Scalable Distributed Stochastic Optimization via Bidirectional Compression: Beyond Pessimistic Limits

    math.OC 2026-05 unverdicted novelty 7.0 of 10

    Inkheart SGD and M4 use bidirectional compression to achieve time complexities in distributed SGD that improve with worker count n and surpass prior lower bounds under a necessary structural assumption.

  5. TCD-Arena: Assessing Robustness of Time Series Causal Discovery Methods Against Assumption Violations

    cs.LG 2026-05 unverdicted novelty 7.0 of 10

    TCD-Arena is a new customizable testing framework that runs millions of experiments to map how 33 different assumption violations affect time series causal discovery methods and shows ensembles can boost overall robustness.

  6. Rescaled Asynchronous SGD: Optimal Distributed Optimization under Data and System Heterogeneity

    cs.LG 2026-05 unverdicted novelty 6.0 of 10

    Rescaled ASGD recovers convergence to the true global objective by rescaling worker stepsizes proportional to computation times, matching the known time lower bound in the leading term under non-convex smoothness and ...

  7. Rennala MVR: Improved Time Complexity for Parallel Stochastic Optimization via Momentum-Based Variance Reduction

    math.OC 2026-05 unverdicted novelty 5.0 of 10

    Rennala MVR improves time complexity over Rennala SGD for smooth nonconvex stochastic optimization in heterogeneous parallel systems under a mean-squared smoothness assumption.

  8. Does Order Matter : Connecting The Law of Robustness to Robust Generalization

    cs.LG 2026-02 reject novelty 4.0 of 10

    The paper proves R(ℓρ∘B_L∘S) ≤ 8R(B_L∘S) but does not derive the advertised Ω(n^{1/d}) recovery or the missing local-scale result.

Pith tools