Universality of high-dimensional scaling limits of stochastic gradient descent

• URL: http://arxiv.org/abs/2512.13634v2
• Date: Sat, 20 Dec 2025 00:03:36 GMT
• Title: Universality of high-dimensional scaling limits of stochastic gradient descent
• Authors: Reza Gheissari, Aukosh Jagannath,
• Abstract summary: We consider tasks in high dimensions whose loss depends on the data only through its projection into a fixed-dimensional subspace spanned by the parameter vectors and certain ground truth vectors.<n>This includes classifying mixture distributions with cross-entropy loss with one and two-layer networks, and learning single and multi-index models with one and two-layer networks.
• Score: 8.760293543857706
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: We consider statistical tasks in high dimensions whose loss depends on the data only through its projection into a fixed-dimensional subspace spanned by the parameter vectors and certain ground truth vectors. This includes classifying mixture distributions with cross-entropy loss with one and two-layer networks, and learning single and multi-index models with one and two-layer networks. When the data is drawn from an isotropic Gaussian mixture distribution, it is known that the evolution of a finite family of summary statistics under stochastic gradient descent converges to an autonomous ordinary differential equation (ODE), as the dimension and sample size go to $\infty$ and the step size goes to $0$ commensurately. Our main result is that these ODE limits are universal in that this limit is the same whenever the data is drawn from mixtures of arbitrary product distributions whose first two moments match the corresponding Gaussian distribution, provided the initialization and ground truth vectors are coordinate-delocalized. We complement this by proving two corresponding non-universality results. We provide a simple example where the ODE limits are non-universal if the initialization is coordinate aligned. We also show that the stochastic differential equation limits arising as fluctuations of the summary statistics around their ODE's fixed points are not universal.

Related papers

• How Does the ReLU Activation Affect the Implicit Bias of Gradient Descent on High-dimensional Neural Network Regression? [27.523011286375947]
  In this paper, we characterize the implicit bias of gradient descent (GD) for training a shallow ReLU model with the squared loss on high-dimensional random features.<n>Our work interpolates between these two extremes and shows that, for sufficiently high-dimensional random data, the implicit bias approximates the minimum-l2-norm solution with high probability.
  arXiv  Detail & Related papers  (2026-03-05T07:36:07Z)
• Consistency of Learned Sparse Grid Quadrature Rules using NeuralODEs [1.3654846342364308]
  This paper provides a proof of the consistency of sparse grid quadrature for numerical integration of high dimensional distributions.<n>A decomposition of the total numerical error in quadrature error and statistical error is provided.
  arXiv  Detail & Related papers  (2025-07-02T09:37:16Z)
• Theory on Score-Mismatched Diffusion Models and Zero-Shot Conditional Samplers [49.97755400231656]
  We present the first performance guarantee with explicit dimensional dependencies for general score-mismatched diffusion samplers.<n>We show that score mismatches result in an distributional bias between the target and sampling distributions, proportional to the accumulated mismatch between the target and training distributions.<n>This result can be directly applied to zero-shot conditional samplers for any conditional model, irrespective of measurement noise.
  arXiv  Detail & Related papers  (2024-10-17T16:42:12Z)
• Computing Marginal and Conditional Divergences between Decomposable Models with Applications [7.89568731669979]
  We propose an approach to compute the exact alpha-beta divergence between any marginal or conditional distribution of two decomposable models. We show how our method can be used to analyze distributional changes by first applying it to a benchmark image dataset. Based on our framework, we propose a novel way to quantify the error in contemporary superconducting quantum computers.
  arXiv  Detail & Related papers  (2023-10-13T14:17:25Z)
• Spectrum-Aware Debiasing: A Modern Inference Framework with Applications to Principal Components Regression [1.342834401139078]
  We introduce SpectrumAware Debiasing, a novel method for high-dimensional regression. Our approach applies to problems with structured, heavy tails, and low-rank structures. We demonstrate our method through simulated and real data experiments.
  arXiv  Detail & Related papers  (2023-09-14T15:58:30Z)
• High-dimensional limit theorems for SGD: Effective dynamics and critical scaling [6.950316788263433]
  We prove limit theorems for the trajectories of summary statistics of gradient descent (SGD) We show a critical scaling regime for the step-size, below which the effective ballistic dynamics matches gradient flow for the population loss. About the fixed points of this effective dynamics, the corresponding diffusive limits can be quite complex and even degenerate.
  arXiv  Detail & Related papers  (2022-06-08T17:42:18Z)
• On the Effective Number of Linear Regions in Shallow Univariate ReLU Networks: Convergence Guarantees and Implicit Bias [50.84569563188485]
  We show that gradient flow converges in direction when labels are determined by the sign of a target network with $r$ neurons. Our result may already hold for mild over- parameterization, where the width is $tildemathcalO(r)$ and independent of the sample size.
  arXiv  Detail & Related papers  (2022-05-18T16:57:10Z)
• GANs as Gradient Flows that Converge [3.8707695363745223]
  We show that along the gradient flow induced by a distribution-dependent ordinary differential equation, the unknown data distribution emerges as the long-time limit. The simulation of the ODE is shown equivalent to the training of generative networks (GANs) This equivalence provides a new "cooperative" view of GANs and, more importantly, sheds new light on the divergence of GANs.
  arXiv  Detail & Related papers  (2022-05-05T20:29:13Z)
• Nonconvex Stochastic Scaled-Gradient Descent and Generalized Eigenvector Problems [98.34292831923335]
  Motivated by the problem of online correlation analysis, we propose the emphStochastic Scaled-Gradient Descent (SSD) algorithm. We bring these ideas together in an application to online correlation analysis, deriving for the first time an optimal one-time-scale algorithm with an explicit rate of local convergence to normality.
  arXiv  Detail & Related papers  (2021-12-29T18:46:52Z)
• On the Double Descent of Random Features Models Trained with SGD [78.0918823643911]
  We study properties of random features (RF) regression in high dimensions optimized by gradient descent (SGD) We derive precise non-asymptotic error bounds of RF regression under both constant and adaptive step-size SGD setting. We observe the double descent phenomenon both theoretically and empirically.
  arXiv  Detail & Related papers  (2021-10-13T17:47:39Z)
• Spectral clustering under degree heterogeneity: a case for the random walk Laplacian [83.79286663107845]
  This paper shows that graph spectral embedding using the random walk Laplacian produces vector representations which are completely corrected for node degree. In the special case of a degree-corrected block model, the embedding concentrates about K distinct points, representing communities.
  arXiv  Detail & Related papers  (2021-05-03T16:36:27Z)
• Benign Overfitting of Constant-Stepsize SGD for Linear Regression [122.70478935214128]
  inductive biases are central in preventing overfitting empirically. This work considers this issue in arguably the most basic setting: constant-stepsize SGD for linear regression. We reflect on a number of notable differences between the algorithmic regularization afforded by (unregularized) SGD in comparison to ordinary least squares.
  arXiv  Detail & Related papers  (2021-03-23T17:15:53Z)
• Understanding Implicit Regularization in Over-Parameterized Single Index Model [55.41685740015095]
  We design regularization-free algorithms for the high-dimensional single index model. We provide theoretical guarantees for the induced implicit regularization phenomenon.
  arXiv  Detail & Related papers  (2020-07-16T13:27:47Z)
• Semiparametric Nonlinear Bipartite Graph Representation Learning with Provable Guarantees [106.91654068632882]
  We consider the bipartite graph and formalize its representation learning problem as a statistical estimation problem of parameters in a semiparametric exponential family distribution. We show that the proposed objective is strongly convex in a neighborhood around the ground truth, so that a gradient descent-based method achieves linear convergence rate. Our estimator is robust to any model misspecification within the exponential family, which is validated in extensive experiments.
  arXiv  Detail & Related papers  (2020-03-02T16:40:36Z)

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.