paper-with-me

홈 › Papers

Gradient descent in Gaussian random fields as a toy model for high-dimensional optimisation in deep learning

2018-03-24 · Mariano Chouza, Stephen Roberts, Stefan Zohren

In this paper we model the loss function of high-dimensional optimization problems by a Gaussian random field, or equivalently a Gaussian process. Our aim is to study gradient descent in such loss functions or energy landscapes and compare it to results obtained from real high-dimensional optimization problems such as encountered in deep learning. In particular, we analyze the distribution of the improved loss function after a step of gradient descent, provide analytic expressions for the moments as well as prove asymptotic normality as the dimension of the parameter space becomes large. Moreover, we compare this with the expectation of the global minimum of the landscape obtained by means of the Euler characteristic of excursion sets. Besides complementing our analytical findings with numerical results from simulated Gaussian random fields, we also compare it to loss functions obtained from optimisation problems on synthetic and real data sets by proposing a "black box" random field toy-model for a deep neural network loss function.

📄 PDF Abstract BibTeX arXiv:1803.09119

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Stochastic Gradient Descent over P2

2026-09-11 · Maria Oprea, Qin Li, Yunan Yang arxiv

Stochastic gradient descent (SGD) admits diffusion approximations that replace the complicated randomness of stochastic gradients by Gaussian noise, providing a powerful tool for understanding its dynamics and long-time …

Stochastic Optimization

Training Conditional Random Fields with Natural Gradient Descent

2015-08-10 · Yuan Cao

We propose a novel parameter estimation procedure that works efficiently for conditional random fields (CRF). This algorithm is an extension to the maximum likelihood estimation (MLE), using loss functions defined by Bre…

parameter estimation

Agnostic Learning of General ReLU Activation Using Gradient Descent

2022-08-04 · Pranjal Awasthi, Alex Tang, Aravindan Vijayaraghavan

We provide a convergence analysis of gradient descent for the problem of agnostically learning a single ReLU function with moderate bias under Gaussian distributions. Unlike prior work that studies the setting of zero bi…

Stochastic Gradient Descent Optimizes Over-parameterized Deep ReLU Networks

2018-11-21 · Difan Zou, Yuan Cao, Dongruo Zhou, Quanquan Gu

We study the problem of training deep neural networks with Rectified Linear Unit (ReLU) activation function using gradient descent and stochastic gradient descent. In particular, we study the binary classification proble…

Binary Classification

Gradient flow in the gaussian covariate model: exact solution of learning curves and multiple descent structures

2022-12-13 · Antoine Bodin, Nicolas Macris

A recent line of work has shown remarkable behaviors of the generalization error curves in simple learning models. Even the least-squares regression has shown atypical features such as the model-wise double descent, and …