paper-with-me

홈 › Papers

The asymptotic spectrum of the Hessian of DNN throughout training

2019-10-01 · ICLR 2020 1 · Arthur Jacot, Franck Gabriel, Clément Hongler

The dynamics of DNNs during gradient descent is described by the so-called Neural Tangent Kernel (NTK). In this article, we show that the NTK allows one to gain precise insight into the Hessian of the cost of DNNs. When the NTK is fixed during training, we obtain a full characterization of the asymptotics of the spectrum of the Hessian, at initialization and during training. In the so-called mean-field limit, where the NTK is not fixed during training, we describe the first two moments of the Hessian at initialization.

📄 PDF Abstract BibTeX arXiv:1910.02875

Code (0)

등록된 구현이 없습니다.

Methods 이 논문이 사용한 방법론

NTK 설명 없음

Similar Papers 제목 키워드 기반

A Teacher-Student Perspective on the Dynamics of Learning Near the Optimal Point

2025-12-17 · Carlos Couto, José Mourão, Mário A. T. Figueiredo, Pedro Ribeiro arxiv

Near an optimal learning point of a neural network, the learning performance of gradient descent dynamics is dictated by the Hessian matrix of the loss function with respect to the network parameters. We characterize the…

An Investigation into Neural Net Optimization via Hessian Eigenvalue Density

2019-01-29 · Behrooz Ghorbani, Shankar Krishnan, Ying Xiao

To understand the dynamics of optimization in deep neural networks, we develop a tool to study the evolution of the entire Hessian spectrum throughout the optimization process. Using this, we study a number of hypotheses…

Universal Asymptotic Optimality of Polyak Momentum

2020-01-01 · ICML 2020 1 · Damien Scieur, Fabian Pedregosa

We consider the average-case runtime analysis of algorithms for minimizing quadratic objectives. In this setting, and contrary to the more classical worst-case analysis, non-asymptotic convergence rates and optimal algor…

Measuring the Spectrum of Deepnet Hessians

2019-05-17 · Vardan Papyan

We apply state-of-the-art tools in modern high-dimensional numerical linear algebra to approximate efficiently the spectrum of the Hessian of modern deepnets, with tens of millions of parameters, trained on real data. We…

Sample Complexity for Quadratic Bandits: Hessian Dependent Bounds and Optimal Algorithms

2023-06-21 · NeurIPS 2023 11 · Qian Yu, Yining Wang, Baihe Huang, Qi Lei 외

In stochastic zeroth-order optimization, a problem of practical relevance is understanding how to fully exploit the local geometry of the underlying objective function. We consider a fundamental setting in which the obje…

valid