A Boundary-Layer Mechanism for One-Third Scaling in Online Softmax Classification

• URL: http://arxiv.org/abs/2605.22341v1
• Date: Thu, 21 May 2026 11:26:32 GMT
• Title: A Boundary-Layer Mechanism for One-Third Scaling in Online Softmax Classification
• Abstract summary: Hardlabel classification is usually trained with smooth surrogate losses, most prominently softmax crossentropy.<n>We isolate an mechanism by which this mismatch between smooth surrogate and discrete labels produces powerlaw learning curves.<n>We show that learning-rate schedules can improve the generalization error towards a $_g sim -1/2$ power law.
• Score: 3.058685580689604
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Hard-label classification is usually trained with smooth surrogate losses, most prominently softmax cross-entropy. We isolate an asymptotic mechanism by which this mismatch between smooth surrogate and discrete labels produces power-law learning curves in an online teacher-student model. After subtracting the mean logit, the thermodynamic-limit dynamics close in centered variables: a growing centered student-teacher alignment $D$ and the residual student variance $Δ$. At late times, examples away from teacher decision boundaries are already classified confidently and contribute exponentially little. Only boundary layers of width $O(D^{-1})$ remain active, while the noise of fixed-learning-rate online gradient descent maintains a nonzero $Δ$. As a function of the training time $α$ the late-time solution yields a $α^{-1/3}$ power law not only for the test loss but also for the generalization error $ε_g$, i.e., one minus test accuracy. This is much slower than the $α^{-1}$ Bayes-optimal reference for the same model. We further show that learning-rate schedules can improve the generalization error towards a $ε_g \sim α^{-1/2}$ power law. Simulations support the predicted order parameter dynamics and learning curves. Controlled experiments with correlated Gaussian inputs and whitened pretrained features show that data structure can dominate transients. Therefore, our result is an asymptotic, complementary mechanism rather than an alternative to spectral explanations of neural scaling laws.

Related papers

• Efficiently Learning Drifting Halfspaces with Massart Noise [50.4331323695175]
  We study the problem of learning a drifting concept in the presence of Massart noise.<n>In this framework, an online learner has access to a history of independent samples.<n>The goal is to output, in each round, a hypothesis with small prediction error.
  arXiv  Detail & Related papers  (2026-06-09T17:35:18Z)
• How Neural Reward Models Learn Features for Policy Optimization: A Single-Index Analysis [53.063298916923976]
  We study the feedback in a Gaussian single-index model with $r*(x) = *(langle *, xrangle)$ and $x sim N(0, I_d)$.<n>We analyze a two-stage neural reward model that first learns the hidden direction $*$ from reward-weighted samples and then fits the readout layer by weighted ridge regression.
  arXiv  Detail & Related papers  (2026-05-23T22:00:38Z)
• Sharp feature-learning transitions and Bayes-optimal neural scaling laws in extensive-width networks [8.250374560598493]
  We study the information-theoretic limits of learning a one-hidden-layer teacher network with hierarchical features from noisy queries.<n>We show that a student trained with textscAdam near the effective width $k_c$ achieves these optimal scaling laws.
  arXiv  Detail & Related papers  (2026-05-11T11:39:03Z)
• The Spectral Edge Thesis: A Mathematical Framework for Intra-Signal Phase Transitions in Neural Network Training [0.0]
  We show that phase transitions in neural network training are controlled by the spectral gap of the rolling-window Gram matrix of parameter updates.<n>Adiabatic parameter $mathcalA = |G|_F / (, g2)$ controls circuit stability: $mathcalA ll 1$ (plateau), $mathcalA sim 1$ (phase transition), $mathcalA gg 1$ (forgetting)
  arXiv  Detail & Related papers  (2026-03-30T20:10:22Z)
• Optimal Unconstrained Self-Distillation in Ridge Regression: Strict Improvements, Precise Asymptotics, and One-Shot Tuning [61.07540493350384]
  Self-distillation (SD) is the process of retraining a student on a mixture of ground-truth and the teacher's own predictions.<n>We show that for any prediction risk, the optimally mixed student improves upon the ridge teacher for every regularization level.<n>We propose a consistent one-shot tuning method to estimate $star$ without grid search, sample splitting, or refitting.
  arXiv  Detail & Related papers  (2026-02-19T17:21:15Z)
• Learning Shrinks the Hard Tail: Training-Dependent Inference Scaling in a Solvable Linear Model [2.7074235008521246]
  We analyze neural scaling laws in a solvable model of last-layer fine-tuning where targets have intrinsic, instance-heterogeneous difficulty.<n>We show that learning shrinks the hard tail'' of the error distribution.
  arXiv  Detail & Related papers  (2026-01-07T10:00:17Z)
• INC: An Indirect Neural Corrector for Auto-Regressive Hybrid PDE Solvers [61.84396402100827]
  We propose the Indirect Neural Corrector ($mathrmINC$), which integrates learned corrections into the governing equations.<n>$mathrmINC$ reduces the error amplification on the order of $t-1 + L$, where $t$ is the timestep and $L$ the Lipschitz constant.<n>We test $mathrmINC$ in extensive benchmarks, covering numerous differentiable solvers, neural backbones, and test cases ranging from a 1D chaotic system to 3D turbulence.
  arXiv  Detail & Related papers  (2025-11-16T20:14:28Z)
• Linear regression with overparameterized linear neural networks: Tight upper and lower bounds for implicit $\ell^1$-regularization [3.4540258577108776]
  We study implicit regularization in diagonal linear neural networks of depth $Dge 2$ for overparameterized linear regression problems.<n>Our results reveal a qualitative difference between depths: for $D ge 3$, the error decreases linearly with $alpha$, whereas for $D=2$, it decreases at rate $alpha1-varrho$.<n> Numerical experiments corroborate our theoretical findings and suggest that deeper networks, i.e., $D ge 3$, may lead to better generalization.
  arXiv  Detail & Related papers  (2025-06-01T19:55:31Z)
• Gradient dynamics for low-rank fine-tuning beyond kernels [9.275532709125242]
  We study low-rank fine-tuning in a student-teacher setting. We prove under mild assumptions that a student model which is matrix at the base model and trained with online gradient descent will converge to the teacher.
  arXiv  Detail & Related papers  (2024-11-23T00:00:28Z)
• Scaling Laws in Linear Regression: Compute, Parameters, and Data [86.48154162485712]
  We study the theory of scaling laws in an infinite dimensional linear regression setup.<n>We show that the reducible part of the test error is $Theta(-(a-1) + N-(a-1)/a)$.<n>Our theory is consistent with the empirical neural scaling laws and verified by numerical simulation.
  arXiv  Detail & Related papers  (2024-06-12T17:53:29Z)
• Locality defeats the curse of dimensionality in convolutional teacher-student scenarios [69.2027612631023]
  We show that locality is key in determining the learning curve exponent $beta$. We conclude by proving, using a natural assumption, that performing kernel regression with a ridge that decreases with the size of the training set leads to similar learning curve exponents to those we obtain in the ridgeless case.
  arXiv  Detail & Related papers  (2021-06-16T08:27:31Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.