A Defense of the Quadratic Model

• URL: http://arxiv.org/abs/2607.21716v1
• Date: Thu, 23 Jul 2026 18:02:03 GMT
• Title: A Defense of the Quadratic Model
• Abstract summary: We stress test the simplest possible model of optimization -- the quadratic model.<n>We show that it can be predictive surprisingly in an LLM setting with 150M parameters and 3B training tokens.
• Score: 71.57026347416729
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Due to the complexity of neural network loss landscapes, optimization theory is forced to rely on idealized models, and there is generally a tradeoff between how theoretically tractable the model is, and how accurately it describes the true optimization dynamics. In this work, we stress test the simplest possible model of optimization -- the quadratic model -- and show that it can be surprisingly predictive in an LLM setting with 150M parameters and 3B training tokens. Specifically, we show that Taylor expanding the model and the loss function at intermediate checkpoints through training can accurately predict the optimization dynamics over windows that can last up to 10\% of training. Having established this agreement, we then turn to analyzing the structure of these local quadratic optimization problems through two lenses: the Hessian spectrum and local stability. Using Lanczos quadrature with extremely deep probes, we are able to estimate the Hessian spectrum deep into the tail, and we find a surprising amount of structure in both the eigenvalues and eigenvectors, which depends on the batch size, preconditioner, and training time. We also empirically test local linear stability at intermediate checkpoints and compare it to theoretical predictions to demonstrate that optimization in LLMs typically occurs at a stochastic edge of stability, whose nature is also determined by batch size. Our results indicate the quadratic model may be a theoretically tractable proxy for pretraining optimization dynamics.

Related papers

• From Atoms to Entropy: Optimal Noise Allocation for Diffusion Training in the Convex Regime [52.459513910242485]
  We develop a general statistical framework for studying optimal noise-level allocation in diffusion training.<n>We show that the optimized training schedule admits an atomic minimizer, concentrated on finitely many noise levels.<n>We then evaluate the entropic schedule in larger-scale experiments, where full schedule optimization is currently intractable.
  arXiv  Detail & Related papers  (2026-07-10T20:59:06Z)
• Linearization Explains Fine-Tuning in Large Language Models [13.157568306905885]
  We show that fine-tuning dynamics become equivalent to learning with the positive-definite neural tangent kernel (NTK)<n>When linearization is a good model, our findings reveal a strong correlation between the eigenvalue spectrum of the NTK and the performance of model adaptation.
  arXiv  Detail & Related papers  (2026-02-09T03:27:58Z)
• ODELoRA: Training Low-Rank Adaptation by Solving Ordinary Differential Equations [54.886931928255564]
  Low-rank adaptation (LoRA) has emerged as a widely adopted parameter-efficient fine-tuning method in deep transfer learning.<n>We propose a novel continuous-time optimization dynamic for LoRA factor matrices in the form of an ordinary differential equation (ODE)<n>We show that ODELoRA achieves stable feature learning, a property that is crucial for training deep neural networks at different scales of problem dimensionality.
  arXiv  Detail & Related papers  (2026-02-07T10:19:36Z)
• How to Set the Learning Rate for Large-Scale Pre-training? [73.03133634525635]
  We formalize this investigation into two distinct research paradigms: Fitting and Transfer.<n>Within the Fitting Paradigm, we introduce a Scaling Law for search factor, effectively reducing the search complexity from O(n3) to O(n*C_D*C_) via predictive modeling.<n>We extend the principles of $$Transfer to the Mixture of Experts (MoE) architecture, broadening its applicability to encompass model depth, weight decay, and token horizons.
  arXiv  Detail & Related papers  (2026-01-08T15:55:13Z)
• Beyond the Ideal: Analyzing the Inexact Muon Update [54.70108543057578]
  We show first analysis of the inexactized update at Muon's core.<n>We reveal a fundamental coupling between this inexactness and the optimal step size and momentum.
  arXiv  Detail & Related papers  (2025-10-22T18:01:07Z)
• Self-Boost via Optimal Retraining: An Analysis via Approximate Message Passing [58.52119063742121]
  Retraining a model using its own predictions together with the original, potentially noisy labels is a well-known strategy for improving the model performance.<n>This paper addresses the question of how to optimally combine the model's predictions and the provided labels.<n>Our main contribution is the derivation of the Bayes optimal aggregator function to combine the current model's predictions and the given labels.
  arXiv  Detail & Related papers  (2025-05-21T07:16:44Z)
• Smart Predict-then-Optimize Method with Dependent Data: Risk Bounds and Calibration of Autoregression [7.369846475695131]
  We present an autoregressive SPO method directly targeting the optimization problem at the decision stage. We conduct experiments to demonstrate the effectiveness of the SPO+ surrogate compared to the absolute loss and the least squares loss.
  arXiv  Detail & Related papers  (2024-11-19T17:02:04Z)
• Towards Stable Machine Learning Model Retraining via Slowly Varying Sequences [6.067007470552307]
  We propose a model-agnostic framework for finding sequences of models that are stable across retraining iterations.<n>We develop a mixed-integer optimization formulation that is guaranteed to recover optimal models.<n>We find that, on average, a 2% reduction in predictive power leads to a 30% improvement in stability.
  arXiv  Detail & Related papers  (2024-03-28T22:45:38Z)
• Structured Optimal Variational Inference for Dynamic Latent Space Models [16.531262817315696]
  We consider a latent space model for dynamic networks, where our objective is to estimate the pairwise inner products plus the intercept of the latent positions. To balance posterior inference and computational scalability, we consider a structured mean-field variational inference framework.
  arXiv  Detail & Related papers  (2022-09-29T22:10:42Z)

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.