paper-with-me

홈 › Papers

Regularizing Deep Neural Networks with Stochastic Estimators of Hessian Trace

2022-08-11 · Yucong Liu, Shixing Yu, Tong Lin

In this paper, we develop a novel regularization method for deep neural networks by penalizing the trace of Hessian. This regularizer is motivated by a recent guarantee bound of the generalization error. We explain its benefits in finding flat minima and avoiding Lyapunov stability in dynamical systems. We adopt the Hutchinson method as a classical unbiased estimator for the trace of a matrix and further accelerate its calculation using a dropout scheme. Experiments demonstrate that our method outperforms existing regularizers and data augmentation methods, such as Jacobian, Confidence Penalty, Label Smoothing, Cutout, and Mixup.

📄 PDF Abstract BibTeX arXiv:2208.05924

Code (1)

iclrsubmission1596/regularizing-deep-neural-networks-with-stochastic-estimators-of-hessian-trace 공식 구현 pytorch

Tasks

Data Augmentation

Methods 이 논문이 사용한 방법론

Label Smoothing Label Smoothing is a regularization technique that introduces noise for the labels. This accounts for the fact that datasets may have mistakes in them, so maximizing the…
Mixup Mixup is a data augmentation technique that generates a weighted combination of random image pairs from the training data. Given two images and their ground truth labels:…
Cutout Cutout is an image augmentation and regularization technique that randomly masks out square regions of input during training. and can be used to improve the robustness and…
Dropout Dropout is a regularization technique for neural networks that drops a unit (along with connections) at training time with a specified probability $p$ (a common value is…

Similar Papers 제목 키워드 기반

On Sharp Stochastic Zeroth Order Hessian Estimators over Riemannian Manifolds

2022-01-26 · Tianyu Wang

We study Hessian estimators for functions defined over an $n$-dimensional complete analytic Riemannian manifold. We introduce new stochastic zeroth-order Hessian estimators using $O (1)$ function evaluations. We show tha…

Generalized Random Direction Newton Algorithms for Stochastic Optimization

2026-02-23 · Soumen Pachal, Prashanth L. A., Shalabh Bhatnagar, Avinash Achar arxiv

We present a family of generalized Hessian estimators of the objective using random direction stochastic approximation (RDSA) by utilizing only noisy function measurements. The form of each estimator and the order of the…

Stochastic Optimization

Stochastic Zeroth Order Gradient and Hessian Estimators: Variance Reduction and Refined Bias Bounds

2022-05-29 · Yasong Feng, Tianyu Wang

We study stochastic zeroth order gradient and Hessian estimators for real-valued functions in $\mathbb{R}^n$. We show that, via taking finite difference along random orthogonal directions, the variance of the stochastic …

An accurate flatness measure to estimate the generalization performance of CNN models

2026-03-09 · Rahman Taleghani, Maryam Mohammadi, Francesco Marchetti arxiv

Flatness measures based on the spectrum or the trace of the Hessian of the loss are widely used as proxies for the generalization ability of deep networks. However, most existing definitions are either tailored to fully …

On the Trajectories of SGD Without Replacement

2023-12-26 · Pierfrancesco Beneventano

This article examines the implicit regularization effect of Stochastic Gradient Descent (SGD). We consider the case of SGD without replacement, the variant typically used to optimize large-scale neural networks. We analy…