Pith. sign in

REVIEW 2 cited by

The Implicit Bias of Depth: How Incremental Learning Drives Generalization

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 1909.12051 v2 pith:LHLENHWL submitted 2019-09-26 cs.LG stat.ML

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

A leading hypothesis for the surprising generalization of neural networks is that the dynamics of gradient descent bias the model towards simple solutions, by searching through the solution space in an incremental order of complexity. We formally define the notion of incremental learning dynamics and derive the conditions on depth and initialization for which this phenomenon arises in deep linear models. Our main theoretical contribution is a dynamical depth separation result, proving that while shallow models can exhibit incremental learning dynamics, they require the initialization to be exponentially small for these dynamics to present themselves. However, once the model becomes deeper, the dependence becomes polynomial and incremental learning can arise in more natural settings. We complement our theoretical findings by experimenting with deep matrix sensing, quadratic neural networks and with binary classification using diagonal and convolutional linear networks, showing all of these models exhibit incremental learning.

Discussion (0). Continue with ORCID 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. Parameter Symmetry Potentially Unifies Deep Learning Theory

    cs.LG 2025-02 conditional novelty 6.0 of 10

    This position paper argues that parameter symmetry breaking and restoration unify three hierarchies in deep learning: learning dynamics, model complexity, and representation formation.

  2. Position: A Theory of Deep Learning Must Include Compositional Sparsity

    cs.LG 2025-07 conditional novelty 4.0 of 10

    All polynomial-time computable functions are compositionally sparse, and this property is the proposed reason deep networks avoid the curse of dimensionality and achieve practical success.

Pith tools