pith. sign in

arxiv: 1811.07062 · v2 · pith:O76ONR6Gnew · submitted 2018-11-16 · 💻 cs.LG · stat.ML

The Full Spectrum of Deepnet Hessians at Scale: Dynamics with SGD Training and Sample Size

classification 💻 cs.LG stat.ML
keywords hessiandynamicsmodernsamplesizespectrumtrainingalgebra
0
0 comments X
read the original abstract

We apply state-of-the-art tools in modern high-dimensional numerical linear algebra to approximate efficiently the spectrum of the Hessian of modern deepnets, with tens of millions of parameters, trained on real data. Our results corroborate previous findings, based on small-scale networks, that the Hessian exhibits "spiked" behavior, with several outliers isolated from a continuous bulk. We decompose the Hessian into different components and study the dynamics with training and sample size of each term individually.

This paper has not been read by Pith yet.

discussion (0)

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

Forward citations

Cited by 9 Pith papers

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

  1. AMUSE: Anytime Muon with Stable Gradient Evaluation

    cs.LG 2026-05 unverdicted novelty 7.0

    AMUSE is a new optimizer integrating Muon orthogonalization with Schedule-Free averaging via adaptive interpolation for schedule-free anytime training that improves Pareto frontiers on vision and LLM tasks.

  2. Fast Gauss-Newton for Multiclass Cross-Entropy

    cs.LG 2026-05 unverdicted novelty 7.0

    FGN is a positive semidefinite under-approximation of the multiclass GGN obtained by exact decomposition into true-vs-rest and within-competitor terms, exact for binary classification and implemented via matrix-free c...

  3. First Exit Time Analysis of Stochastic Gradient Descent Under Heavy-Tailed Gradient Noise

    stat.ML 2019-06 unverdicted novelty 7.0

    Derives explicit step-size conditions ensuring the metastability behavior of discrete SGD under heavy-tailed noise approximates its continuous SDE limit.

  4. Generalization at the Edge of Stability

    cs.LG 2026-04 unverdicted novelty 6.0

    Training at the edge of stability causes neural network optimizers to converge on fractal attractors whose effective dimension, measured via a new sharpness dimension from the Hessian spectrum, bounds generalization e...

  5. Low Rank Based Subspace Inference for the Laplace Approximation of Bayesian Neural Networks

    cs.LG 2025-02 unverdicted novelty 6.0

    Derives optimal low-rank subspace for Laplace approx in BNNs, provides scalable outperforming version, and new comparison metric.

  6. Language Models (Mostly) Know What They Know

    cs.CL 2022-07 unverdicted novelty 6.0

    Language models show good calibration when asked to estimate the probability that their own answers are correct, with performance improving as models get larger.

  7. A General Language Assistant as a Laboratory for Alignment

    cs.CL 2021-12 conditional novelty 6.0

    Ranked preference modeling outperforms imitation learning for language model alignment and scales more favorably with model size.

  8. Scaling Laws for Transfer

    cs.LG 2021-02 unverdicted novelty 6.0

    Effective data transferred from pre-training to fine-tuning is described by a power law in model parameter count and fine-tuning dataset size, acting like a multiplier on the fine-tuning data.

  9. Hessian based analysis of SGD for Deep Nets: Dynamics and Generalization

    cs.LG 2019-07 unverdicted novelty 4.0

    Provides Hessian-based theoretical characterizations of SGD dynamics and a scale-invariant generalization bound for deep nets, backed by experiments on synthetic data, MNIST, and CIFAR-10.