Why resnet works? residuals generalize

F He, T Liu, D Tao - IEEE transactions on neural networks and …, 2020‏ - ieeexplore.ieee.org
Residual connections significantly boost the performance of deep neural networks.
However, few theoretical results address the influence of residuals on the hypothesis …

Stable and fair classification

L Huang, N Vishnoi - International Conference on Machine …, 2019‏ - proceedings.mlr.press
In a recent study, Friedler et al. pointed out that several fair classification algorithms are not
stable with respect to variations in the training set–a crucial consideration in several …

[HTML][HTML] Overfit detection method for deep neural networks trained to beamform ultrasound images

J Zhang, MAL Bell - Ultrasonics, 2025‏ - Elsevier
Deep neural networks (DNNs) have remarkable potential to reconstruct ultrasound images.
However, this promise can suffer from overfitting to training data, which is typically detected …

Stability and generalization for randomized coordinate descent

P Wang, L Wu, Y Lei - arxiv preprint arxiv:2108.07414, 2021‏ - arxiv.org
Randomized coordinate descent (RCD) is a popular optimization algorithm with wide
applications in solving various machine learning problems, which motivates a lot of …

Characterization of excess risk for locally strongly convex population risk

M Yi, R Wang, ZM Ma - Advances in Neural Information …, 2022‏ - proceedings.neurips.cc
We establish upper bounds for the expected excess risk of models trained by proper iterative
algorithms which approximate the local minima. Unlike the results built upon the strong …

Subsampling oriented active learning method for multi-category classification problem.

SHI Wei, H Honglan, F Yanghe… - Systems Engineering …, 2021‏ - search.ebscohost.com
Because the computational amount of the traditional active learning method increases
exponentially with the increase of problem size, it is difficult to apply to the large-scale multi …

The Impact of the Mini-batch Size on the Dynamics of SGD: Variance and Beyond

X Qian, D Klabjan‏ - openreview.net
We study mini-batch stochastic gradient descent (SGD) dynamics under linear regression
and deep linear networks by focusing on the variance of the gradients only given the initial …

[ספר][B] Efficient Stochastic Optimization Algorithms for Large-Scale Machine Learning Problems

C Tan - 2019‏ - search.proquest.com
Due to rapid growth in the data size, it becomes a more and more challenging issue
concerning how to train machine learning models efficiently. In many industry applications, it …

[PDF][PDF] Exploring the Generalization Performance of Neural Networks via Diversity.

T Niu, J Zhang, P Zhang - Aust. J. Intell. Inf. Process. Syst., 2019‏ - scholar.archive.org
Neural networks (NNs) have achieved excellent performance in many industrial tasks, but
their interpretability is still a major challenge and difficulty, in which the generalization ability …

[CITATION][C] Challenges of statistical machine learning when encountered deep neural network

Q Meng - 2024‏ - Elsevier