Pith. sign in

REVIEW 5 cited by

The Deep Bootstrap Framework: Good Online Learners are Good Offline Generalizers

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 2010.08127 v2 pith:I3EZRICW submitted 2020-10-16 cs.LG cs.CVcs.NEmath.STstat.MLstat.TH

The Deep Bootstrap Framework: Good Online Learners are Good Offline Generalizers

classification cs.LG cs.CVcs.NEmath.STstat.MLstat.TH
keywords learningworlddeepframeworkgeneralizationideallossempirical
verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved
0 comments
read the original abstract

We propose a new framework for reasoning about generalization in deep learning. The core idea is to couple the Real World, where optimizers take stochastic gradient steps on the empirical loss, to an Ideal World, where optimizers take steps on the population loss. This leads to an alternate decomposition of test error into: (1) the Ideal World test error plus (2) the gap between the two worlds. If the gap (2) is universally small, this reduces the problem of generalization in offline learning to the problem of optimization in online learning. We then give empirical evidence that this gap between worlds can be small in realistic deep learning settings, in particular supervised image classification. For example, CNNs generalize better than MLPs on image distributions in the Real World, but this is "because" they optimize faster on the population loss in the Ideal World. This suggests our framework is a useful tool for understanding generalization in deep learning, and lays a foundation for future research in the area.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 5 Pith papers

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

  1. Model-based Bootstrap of Controlled Markov Chains

    stat.ML 2026-05 accept novelty 7.0

    A model-based bootstrap for finite CMCs is distributionally consistent for transitions and, via the delta method, for OPE/OPR targets under nonstationary behavior policies.

  2. Manifold Steering Reveals the Shared Geometry of Neural Network Representation and Behavior

    cs.LG 2026-05 unverdicted novelty 7.0

    Manifold steering along activation geometry induces behavioral trajectories matching the natural manifold of outputs, while linear steering produces off-manifold unnatural behaviors.

  3. Theory of Optimal Learning Rate Schedules and Scaling Laws for a Random Feature Model

    cond-mat.dis-nn 2026-02 unverdicted novelty 7.0

    In a random feature model, optimal SGD learning-rate schedules are polynomial decay in the easy phase and warmup-stable-decay in the hard phase, outperforming constant or simple power-law schedules and transferring di...

  4. Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models

    cs.CL 2022-06 accept novelty 7.0

    BIG-bench is a 204-task benchmark that measures scaling trends, calibration, and absolute limitations of language models across knowledge, reasoning, and social domains.

  5. Model-based Bootstrap of Controlled Markov Chains

    stat.ML 2026-05 unverdicted novelty 6.0

    A model-based bootstrap achieves distributional consistency for transition estimators in controlled Markov chains with unknown policies and yields asymptotically valid confidence intervals for offline policy evaluatio...