paper-with-me

Papers

Large Spikes in Stochastic Gradient Descent: A Large-Deviations View

2026-03-10 · Benjamin Gess, Daniel Heydecker arxiv

Large loss spikes in stochastic gradient descent are studied through a rigorous large-deviations analysis for a shallow, fully connected network in the NTK scaling. In contrast to full-batch gradient descent, the catapult phase is shown to split into inflationary and deflationary regimes, determined by an explicit log-drift criterion. In both cases, large spikes are shown to be at least polynomially likely. In addition, these spikes are shown to be the dominant mechanism by which sharp minima are escaped and curvature is reduced, thereby favouring flatter solutions. Corresponding results are also obtained for certain ReLU networks, and implications for curriculum learning are derived.

📄 PDF Abstract BibTeX arXiv:2603.10079

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Catapults in SGD: spikes in the training loss and their impact on generalization through feature learning

2023-06-07 · Libin Zhu, Chaoyue Liu, Adityanarayanan Radhakrishnan, Mikhail Belkin

In this paper, we first present an explanation regarding the common occurrence of spikes in the training loss when neural networks are trained with stochastic gradient descent (SGD). We provide evidence that the spikes i…

Fast off-the-grid sparse recovery with over-parametrized projected gradient descent

2022-02-28 · Pierre-Jean Bénard, Yann Traonmilin, Jean-François Aujol

We consider the problem of recovering off-the-grid spikes from Fourier measurements. Successful methods such as sliding Frank-Wolfe and continuous orthogonal matching pursuit (OMP) iteratively add spikes to the solution …

Stochastic gradient descent in high dimensions for multi-spiked tensor PCA

2024-10-23 · Gérard Ben Arous, Cédric Gerbelot, Vanessa Piccolo

We study the dynamics in high dimensions of online stochastic gradient descent for the multi-spiked tensor model. This multi-index model arises from the tensor principal component analysis (PCA) problem with multiple spi…

Smooth Exact Gradient Descent Learning in Spiking Neural Networks

2023-09-25 · Christian Klos, Raoul-Martin Memmesheimer

Gradient descent prevails in artificial neural network training, but seems inept for spiking neural networks as small parameter changes can cause sudden, disruptive (dis-)appearances of spikes. Here, we demonstrate exact…

Percolation Dynamics in Optimization : Variance Cascades and Discrete Scale Invariance

2026-09-02 · Sai Niranjan Ramachandran, Suvrit Sra hf

We study the dynamics of Stochastic Gradient Descent (SGD), which is known to steer deep neural networks toward invariant sets that correspond to simpler subnetworks. How this steering unfolds over time remains poorly un…