pith. sign in

arxiv: 2002.09572 · v1 · pith:MNCTPPW4new · submitted 2020-02-21 · 💻 cs.LG · stat.ML

The Break-Even Point on Optimization Trajectories of Deep Neural Networks

classification 💻 cs.LG stat.ML
keywords phasetrainingbreak-evenearlygradientlossneuraloptimization
0
0 comments X
read the original abstract

The early phase of training of deep neural networks is critical for their final performance. In this work, we study how the hyperparameters of stochastic gradient descent (SGD) used in the early phase of training affect the rest of the optimization trajectory. We argue for the existence of the "break-even" point on this trajectory, beyond which the curvature of the loss surface and noise in the gradient are implicitly regularized by SGD. In particular, we demonstrate on multiple classification tasks that using a large learning rate in the initial phase of training reduces the variance of the gradient, and improves the conditioning of the covariance of gradients. These effects are beneficial from the optimization perspective and become visible after the break-even point. Complementing prior work, we also show that using a low learning rate results in bad conditioning of the loss surface even for a neural network with batch normalization layers. In short, our work shows that key properties of the loss surface are strongly influenced by SGD in the early phase of training. We argue that studying the impact of the identified effects on generalization is a promising future direction.

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 6 Pith papers

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

  1. The Spectral Lifecycle of Transformer Training: Transient Compression Waves, Persistent Spectral Gradients, and the Q/K--V Asymmetry

    cs.LG 2026-04 unverdicted novelty 8.0

    Transformer weight spectra exhibit transient compression waves that propagate layer-wise, persistent non-monotonic depth gradients in power-law exponents, and Q/K-V asymmetry, with the spectral exponent alpha predicti...

  2. Momentum Further Constrains Sharpness at the Edge of Stochastic Stability

    cs.LG 2026-04 unverdicted novelty 7.0

    Momentum SGD exhibits two distinct EoSS regimes for batch sharpness, stabilizing at 2(1-β)/η for small batches and 2(1+β)/η for large batches, aligning with linear stability thresholds.

  3. Edge of Stability Selectively Shapes Learning Across the Data Distribution

    cs.LG 2026-06 unverdicted novelty 6.0

    Edge of stability acts as a selective mechanism that amplifies learning on data groups with aligned persistent gradients while suppressing others.

  4. Does Weight Decay Enhance Training Stability?

    cs.LG 2026-05 conditional novelty 6.0

    Weight decay slows progressive sharpening at the edge of stability, inducing damped oscillations in CNNs and a phase transition to sub-2/η sharpness in MLPs driven by parameter-sharpness gradient alignment, yielding m...

  5. 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...

  6. There Will Be a Scientific Theory of Deep Learning

    stat.ML 2026-04 unverdicted novelty 2.0

    A mechanics of the learning process is emerging in deep learning theory, characterized by dynamics, coarse statistics, and falsifiable predictions across idealized settings, limits, laws, hyperparameters, and universa...