Closed-Form Steepest Descent Direction toward Flat Minima: Reducing Upper Bounds on the Loss Hessian Eigenspectrum in Neural Networks

• URL: http://arxiv.org/abs/2606.28662v1
• Date: Sat, 27 Jun 2026 00:47:03 GMT
• Title: Closed-Form Steepest Descent Direction toward Flat Minima: Reducing Upper Bounds on the Loss Hessian Eigenspectrum in Neural Networks
• Abstract summary: We analytically derive the gradient of the WS upper bound to characterize directions leading to flat minima.<n> Experiments demonstrate that HSR Regularization narrows the Hessian eigenvalue spectrum, avoids sharp minima and saddle points, and promotes convergence to flat minima.
• Score: 3.011579195399507
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: The flatness hypothesis suggests that flatness of the loss landscape, as measured by the eigenvalues of the loss Hessian, correlates with better neural network generalization. While various algorithms reduce these eigenvalues, most focus on procedural design, leaving it unclear how data distributions and NN parameters structurally determine directions toward flat minima. Characterizing these directions analytically is generally intractable. To overcome this mathematical difficulty, recent studies derived the Wolkowicz-Styan (WS) upper bound on the maximum eigenvalue of the cross-entropy loss Hessian in three-layer NNs. Although this upper bound is differentiable, its gradient was not derived. Therefore, we analytically derive the gradient of the WS upper bound to characterize directions leading to flat minima. Based on this, we propose Hessian Spectral Range (HSR) Regularization, which updates parameters along the steepest descent direction of the WS bound. Experiments demonstrate that HSR Regularization narrows the Hessian eigenvalue spectrum, avoids sharp minima and saddle points, and promotes convergence to flat minima. Although the applicability of this method is currently limited to cross-entropy loss and three-layer architectures, to the best of the authors' knowledge, this is the first study to report a closed-form gradient that promotes convergence to flat minima without numerical approximations. Therefore, the theoretical analysis of this gradient is expected to contribute to the further development of NNs.

Related papers

• Across the Loss Landscape with Progressive Growth [51.366966420881646]
  We show how grow-and-optimize strategies to train toward flatter regions by viewing growth as progressive relaxation.<n>We empirically validate these predictions in controlled toy basins and in a realistic ResNet/CI-100 setting.<n>Although progressive subspace growth reliably produces flatter solutions, curvature reductions do not universally translate into improved test performance, highlighting subtleties in the flatness-generalization connection.
  arXiv  Detail & Related papers  (2026-08-25T13:50:48Z)
• Fisher-Geometric Sharpness and the Implicit Bias of SGD toward Flat Minima [0.0]
  gradient descent (SGD) implicitly favors flat minima.<n>We prove that it is invariant under smooth, function-preserving reparametrizations.<n>Experiments on MNIST and CIFAR-10 confirm that SR reliably tracks generalization in ways that Euclidean sharpness does not.
  arXiv  Detail & Related papers  (2026-06-18T16:48:18Z)
• SDS-LoRA: Overcoming Anisotropic Gradient Scaling in Low-Rank Adaptation [64.33799467286265]
  Low-Rank Adaptation (LoRA) enables efficient adaptation of large pre-trained models to downstream tasks.<n>We show that when a full fine-tuning gradient is backpropagated to the low-rank matrices, it undergoes anisotropic scaling driven by their singular values.<n>We propose a new low-rank parameterization, SDS-LoRA, which structurally decouples singular values from the backward pass.
  arXiv  Detail & Related papers  (2026-06-15T09:27:50Z)
• Wolkowicz-Styan Upper Bound on the Hessian Eigenspectrum for Cross-Entropy Loss in Nonlinear Smooth Neural Networks [3.011579195399507]
  Relationship between loss geometry and generalization is still not well understood.<n>This study focuses on nonlinear, smooth multilayer neural networks and derives a closed-form upper bound for the maximum eigenvalue of the Hessian.<n>The derived upper bound is expressed as a function of the affine transformation parameters, hidden layer dimensions, and the degree of computationity among the training samples.
  arXiv  Detail & Related papers  (2026-04-11T13:16:29Z)
• Revisiting Zeroth-Order Optimization: Minimum-Variance Two-Point Estimators and Directionally Aligned Perturbations [57.179679246370114]
  We identify the distribution of random perturbations that minimizes the estimator's variance as the perturbation stepsize tends to zero.<n>Our findings reveal that such desired perturbations can align directionally with the true gradient, instead of maintaining a fixed length.
  arXiv  Detail & Related papers  (2025-10-22T19:06:39Z)
• Convergence Rates for Gradient Descent on the Edge of Stability in Overparametrised Least Squares [33.60489399178793]
  gradient descent on neural networks is frequently performed in a large step size regime called the edge of stability"<n>We provide convergence rates for gradient descent with large learning rates in an overparametrised least squares setting.
  arXiv  Detail & Related papers  (2025-10-20T13:02:41Z)
• Stable Minima of ReLU Neural Networks Suffer from the Curse of Dimensionality: The Neural Shattering Phenomenon [25.998397575754865]
  We study the implicit bias of flatness / low (loss) curvature and its effects on generalization in ReLU networks.<n>We show that while flatness does imply generalization, the resulting rates of convergence necessarily deteriorate exponentially as the input dimension grows.
  arXiv  Detail & Related papers  (2025-06-25T19:10:03Z)
• A Mean-Field Analysis of Neural Stochastic Gradient Descent-Ascent for Functional Minimax Optimization [90.87444114491116]
  This paper studies minimax optimization problems defined over infinite-dimensional function classes of overparametricized two-layer neural networks. We address (i) the convergence of the gradient descent-ascent algorithm and (ii) the representation learning of the neural networks. Results show that the feature representation induced by the neural networks is allowed to deviate from the initial one by the magnitude of $O(alpha-1)$, measured in terms of the Wasserstein distance.
  arXiv  Detail & Related papers  (2024-04-18T16:46:08Z)
• On the Convergence of Gradient Descent for Large Learning Rates [55.33626480243135]
  We show that convergence is impossible when a fixed step size is used.<n>We provide a proof of this in the case of linear neural networks with a squared loss.<n>We also prove the impossibility of convergence for more general losses without requiring strong assumptions such as Lipschitz continuity for the gradient.
  arXiv  Detail & Related papers  (2024-02-20T16:01:42Z)
• Implicit regularization in AI meets generalized hardness of approximation in optimization -- Sharp results for diagonal linear networks [0.0]
  We show sharp results for the implicit regularization imposed by the gradient flow of Diagonal Linear Networks. We link this to the phenomenon of phase transitions in generalized hardness of approximation. Non-sharpness of our results would imply that the GHA phenomenon would not occur for the basis pursuit optimization problem.
  arXiv  Detail & Related papers  (2023-07-13T13:27:51Z)
• Last-Iterate Convergence of Adaptive Riemannian Gradient Descent for Equilibrium Computation [52.73824786627612]
  This paper establishes new convergence results for textitgeodesic strongly monotone games.<n>Our key result shows that RGD attains last-iterate linear convergence in a textitgeometry-agnostic fashion.<n>Overall, this paper presents the first geometry-agnostic last-iterate convergence analysis for games beyond the Euclidean settings.
  arXiv  Detail & Related papers  (2023-06-29T01:20:44Z)
• The Inductive Bias of Flatness Regularization for Deep Matrix Factorization [58.851514333119255]
  This work takes the first step toward understanding the inductive bias of the minimum trace of the Hessian solutions in deep linear networks. We show that for all depth greater than one, with the standard Isometry Property (RIP) on the measurements, minimizing the trace of Hessian is approximately equivalent to minimizing the Schatten 1-norm of the corresponding end-to-end matrix parameters.
  arXiv  Detail & Related papers  (2023-06-22T23:14:57Z)
• Beyond the Edge of Stability via Two-step Gradient Updates [49.03389279816152]
  Gradient Descent (GD) is a powerful workhorse of modern machine learning. GD's ability to find local minimisers is only guaranteed for losses with Lipschitz gradients. This work focuses on simple, yet representative, learning problems via analysis of two-step gradient updates.
  arXiv  Detail & Related papers  (2022-06-08T21:32:50Z)

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.