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

arXiv: https://arxiv.org/abs/2606.28662 · HTML: https://mlsanity.com/paper/2606.28662/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 30 of its 40 references that are in the map.
- First posted on arXiv 27 Jun 2026.

## Builds on (most cited first, 30 of 30)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [Sharpness-Aware Minimization for Efficiently Improving Generalization](https://mlsanity.com/paper/2010.01412/) (2020)
- [On Large-Batch Training for Deep Learning: Generalization Gap and Sharp Minima](https://mlsanity.com/paper/1609.04836/) (2016)
- [Visualizing the Loss Landscape of Neural Nets](https://mlsanity.com/paper/1712.09913/) (2017)
- [Sharp Minima Can Generalize For Deep Nets](https://mlsanity.com/paper/1703.04933/) (2017)
- [ASAM: Adaptive Sharpness-Aware Minimization for Scale-Invariant Learning of Deep Neural Networks](https://mlsanity.com/paper/2102.11600/) (2021)
- [An Investigation into Neural Net Optimization via Hessian Eigenvalue Density](https://mlsanity.com/paper/1901.10159/) (2019)
- [PyHessian: Neural Networks Through the Lens of the Hessian](https://mlsanity.com/paper/1912.07145/) (2019)
- [HAWQ-V2: Hessian Aware trace-Weighted Quantization of Neural Networks](https://mlsanity.com/paper/1911.03852/) (2019)
- [When Vision Transformers Outperform ResNets without Pre-training or Strong Data Augmentations](https://mlsanity.com/paper/2106.01548/) (2021)
- [Eigenvalues of the Hessian in Deep Learning: Singularity and Beyond](https://mlsanity.com/paper/1611.07476/) (2016)
- [Towards Understanding Sharpness-Aware Minimization](https://mlsanity.com/paper/2206.06232/) (2022)
- [Understanding Gradient Descent on Edge of Stability in Deep Learning](https://mlsanity.com/paper/2205.09745/) (2022)
- [Traces of Class/Cross-Class Structure Pervade Deep Learning Spectra](https://mlsanity.com/paper/2008.11865/) (2020)
- [Understanding the Generalization Benefit of Normalization Layers: Sharpness Reduction](https://mlsanity.com/paper/2206.07085/) (2022)
- [Analytic Insights into Structure and Rank of Neural Network Hessian Maps](https://mlsanity.com/paper/2106.16225/) (2021)
- [A Review of Deep Learning Techniques for Speech Processing](https://mlsanity.com/paper/2305.00359/) (2023)
- [Dissecting Hessian: Understanding Common Structure of Hessian in Neural Networks](https://mlsanity.com/paper/2010.04261/) (2020)
- [A Deeper Look at the Hessian Eigenspectrum of Deep Neural Networks and its Applications to Regularization](https://mlsanity.com/paper/2012.03801/) (2020)
- [The Implicit Regularization of Dynamical Stability in Stochastic Gradient Descent](https://mlsanity.com/paper/2305.17490/) (2023)
- [ImbSAM: A Closer Look at Sharpness-Aware Minimization in Class-Imbalanced Recognition](https://mlsanity.com/paper/2308.07815/) (2023)
- [Explicit Eigenvalue Regularization Improves Sharpness-Aware Minimization](https://mlsanity.com/paper/2501.12666/) (2025)
- [How noise affects the Hessian spectrum in overparameterized neural networks](https://mlsanity.com/paper/1910.00195/) (2019)
- [On the Power-Law Hessian Spectrums in Deep Learning](https://mlsanity.com/paper/2201.13011/) (2022)
- [Noise Stability Optimization for Finding Flat Minima: A Hessian-based Regularization Approach](https://mlsanity.com/paper/2306.08553/) (2023)
- [Learning Models over Relational Data using Sparse Tensors and Functional Dependencies](https://mlsanity.com/paper/1703.04780/) (2017)
- [SALR: Sharpness-aware Learning Rate Scheduler for Improved Generalization](https://mlsanity.com/paper/2011.05348/) (2020)
- [From Sharpness to Better Generalization for Speech Deepfake Detection](https://mlsanity.com/paper/2506.11532/) (2025)
- [Wolkowicz-Styan Upper Bound on the Hessian Eigenspectrum for Cross-Entropy Loss in Nonlinear Smooth Neural Networks](https://mlsanity.com/paper/2604.10202/) (2026)

## Abstract (arXiv)

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.