Pith. sign in

REVIEW 10 cited by

Deep Double Descent: Where Bigger Models and More Data Hurt

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 1912.02292 v1 pith:NAFXKFON submitted 2019-12-04 cs.LG cs.CVcs.NEstat.ML

classification cs.LGcs.CVcs.NEstat.ML
keywords modelcomplexitydescentdoubledeepfunctiongetsmeasure
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

We show that a variety of modern deep learning tasks exhibit a "double-descent" phenomenon where, as we increase model size, performance first gets worse and then gets better. Moreover, we show that double descent occurs not just as a function of model size, but also as a function of the number of training epochs. We unify the above phenomena by defining a new complexity measure we call the effective model complexity and conjecture a generalized double descent with respect to this measure. Furthermore, our notion of model complexity allows us to identify certain regimes where increasing (even quadrupling) the number of train samples actually hurts test performance.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 10 Pith papers

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

  1. Impact of Bottleneck Layers and Skip Connections on the Generalization of Linear Denoising Autoencoders

    stat.ML 2025-05 conditional novelty 7.0 of 10

    Two-layer linear denoising autoencoders show a bias-variance trade-off in bottleneck width, and skip connections reduce variance near the interpolation peak.

  2. Breaking the Simplification Bottleneck in Amortized Neural Symbolic Regression

    cs.LG 2026-02 conditional novelty 6.0 of 10

    A fast hash-based simplification engine enables a transformer-based symbolic regression system to train on 512M simplified expressions and match PySR on the FastSRB benchmark with better parsimony scaling.

  3. On Spectral Properties of Gradient-based Explanation Methods

    cs.LG 2025-08 conditional novelty 6.0 of 10

    Gradient-based explanations behave like frequency-band selectors: the gradient acts as a high-pass filter, perturbation as a low-pass filter, and their combination creates explanations that shift with the perturbation scale.

  4. Detecting AI Assistance in Abstract Complex Tasks

    cs.AI 2025-07 reject novelty 6.0 of 10

    Converting behavioral search traces into image channels plus an exploration/exploitation time series lets a small CNN-RNN detect AI assistance with about 86% accuracy on a balanced lab task.

  5. How much do language models memorize?

    cs.CL 2025-05 conditional novelty 6.0 of 10

    A compression-based measurement puts GPT-style model memorization capacity at roughly 3.6 bits per parameter, with membership inference success following a sigmoid in the dataset-to-capacity ratio.

  6. Double Descent and Overparameterization in Particle Physics Data

    hep-ex 2025-09 conditional novelty 5.0 of 10

    Double descent, a test-error peak followed by recovery at high capacity, appears in jet regression and event classification on ATLAS open data; with early stopping, overparameterized models can beat classical ones.

  7. BlueGlass: A Framework for Composite AI Safety

    cs.AI 2025-07 conditional novelty 5.0 of 10

    BlueGlass provides composite AI safety infrastructure; its case studies on object-detection VLMs reveal dataset trade-offs, a decoder-layer phase transition in probe accuracy, and SAE-discovered concepts including spu...

  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.

  9. Optimizers Qualitatively Alter Solutions And We Should Leverage This

    cs.LG 2025-07 conditional novelty 4.0 of 10

    Deep learning optimizers should be designed to induce desired solution properties, not just convergence speed; different optimizers demonstrably land in qualitatively different minima.

  10. Statistical Machine Learning for Astronomy -- A Textbook

    astro-ph.IM 2025-06 unverdicted

    A systematic Bayesian-first textbook that derives classical and modern machine learning methods for astronomy from probability theory, explicitly without new research results.

Pith tools