English
Related papers

Related papers: On the Convergence of (Stochastic) Gradient Descen…

200 papers

Kolmogorov-Arnold Networks represent a recent advancement in machine learning, with the potential to outperform traditional perceptron-based neural networks across various domains as well as provide more interpretability with the use of…

High Energy Physics - Phenomenology · Physics 2024-09-26 E. Abasov , P. Volkov , G. Vorotnikov , L. Dudko , A. Zaborenko , E. Iudin , A. Markina , M. Perfilov

We present, QP-SBGD, a novel layer-wise stochastic optimiser tailored towards training neural networks with binary weights, known as binary neural networks (BNNs), on quantum hardware. BNNs reduce the computational requirements and energy…

Computer Vision and Pattern Recognition · Computer Science 2024-09-05 Maximilian Krahn , Michele Sasdelli , Fengyi Yang , Vladislav Golyanik , Juho Kannala , Tat-Jun Chin , Tolga Birdal

Physics-Informed Neural Networks (PINNs) have become a popular and powerful framework for solving partial differential equations (PDEs), leveraging neural networks to approximate solutions while embedding PDE constraints, boundary…

Numerical Analysis · Mathematics 2026-02-03 Zijuan Xin , Chenyao Wang , Feng Shi , Yizhong Sun

In this paper we analyze the behaviour of the stochastic gradient descent (SGD), a widely used method in supervised learning for optimizing neural network weights via a minimization of non-convex loss functions. Since the pioneering work of…

Machine Learning · Computer Science 2025-05-13 Davide Barbieri , Matteo Bonforte , Peio Ibarrondo

In this paper, we introduce a probabilistic extension to Kolmogorov Arnold Networks (KANs) by incorporating Gaussian Process (GP) as non-linear neurons, which we refer to as GP-KAN. A fully analytical approach to handling the output…

Machine Learning · Computer Science 2024-08-20 Andrew Siyuan Chen

Training deep neural networks with stochastic gradient descent (SGD) can often achieve zero training loss on real-world tasks although the optimization landscape is known to be highly non-convex. To understand the success of SGD for…

Machine Learning · Statistics 2020-06-15 Yiping Lu , Chao Ma , Yulong Lu , Jianfeng Lu , Lexing Ying

In this article we study the stochastic gradient descent (SGD) optimization method in the training of fully-connected feedforward artificial neural networks with ReLU activation. The main result of this work proves that the risk of the SGD…

Numerical Analysis · Mathematics 2022-09-28 Arnulf Jentzen , Adrian Riekert

Neural network (NN)-based transistor compact modeling has recently emerged as a transformative solution for accelerating device modeling and SPICE circuit simulations. However, conventional NN architectures, despite their widespread…

Machine Learning · Computer Science 2025-03-20 Rodion Novkin , Hussam Amrouch

Stochastic Gradient Descent (SGD) is a central tool in machine learning. We prove that SGD converges to zero loss, even with a fixed (non-vanishing) learning rate - in the special case of homogeneous linear classifiers with smooth monotone…

Machine Learning · Statistics 2022-04-19 Mor Shpigel Nacson , Nathan Srebro , Daniel Soudry

Kolmogorov-Arnold Networks (KANs) have seen great success in scientific domains thanks to spline activation functions, becoming an alternative to Multi-Layer Perceptrons (MLPs). However, spline functions may not respect symmetry in tasks,…

Machine Learning · Computer Science 2025-08-18 Lexiang Hu , Yisen Wang , Zhouchen Lin

The highly nonlinear degradation process, complex physical interactions, and various sources of uncertainty render single-image Super-resolution (SR) a particularly challenging task. Existing interpretable SR approaches, whether based on…

Computer Vision and Pattern Recognition · Computer Science 2025-12-30 Chenyu Li , Danfeng Hong , Bing Zhang , Zhaojie Pan , Jocelyn Chanussot

This work focuses on the behavior of stochastic gradient descent (SGD) in solving least-squares regression with physics-informed neural networks (PINNs). Past work on this topic has been based on the over-parameterization regime, whose…

Machine Learning · Computer Science 2025-07-23 Zhihan Zeng , Yiqi Gu

The present paper introduces concurrency-driven enhancements to the training algorithm for the Kolmogorov-Arnold networks (KANs) that is based on the Newton-Kaczmarz (NK) method. Prior research shows that KANs trained using the NK-based…

Machine Learning · Computer Science 2026-03-30 Andrew Polar , Michael Poluektov

Neural network optimization remains one of the most consequential yet poorly understood challenges in modern AI research, where improvements in training algorithms can lead to enhanced feature learning in foundation models,…

Machine Learning · Computer Science 2025-12-23 Ansh Nagwekar

Kolmogorov-Arnold Networks (KANs) offer a promising framework for approximating complex nonlinear functions, yet the original B-spline formulation suffers from significant computational overhead due to De Boor algorithm. While recent…

Machine Learning · Computer Science 2026-02-10 Shao-Ting Chiu , Siu Wun Cheung , Ulisses Braga-Neto , Chak Shing Lee , Rui Peng Li

In this paper, we consider a general stochastic optimization problem which is often at the core of supervised learning, such as deep learning and linear classification. We consider a standard stochastic gradient descent (SGD) method with a…

Machine Learning · Statistics 2018-12-27 Lam M. Nguyen , Nam H. Nguyen , Dzung T. Phan , Jayant R. Kalagnanam , Katya Scheinberg

Convolutional Neural Networks (CNNs) and vision transformers (ViTs) have shown excellent capability in complex hyperspectral image (HSI) classification. However, these models require a significant number of training data and are…

Computer Vision and Pattern Recognition · Computer Science 2024-06-25 Ali Jamali , Swalpa Kumar Roy , Danfeng Hong , Bing Lu , Pedram Ghamisi

Kolmogorov-Arnold Networks (KAN) are a new class of neural network architecture representing a promising alternative to the Multilayer Perceptron (MLP), demonstrating improved expressiveness and interpretability. However, KANs suffer from…

Machine Learning · Computer Science 2025-03-04 Cale Coffman , Lizhong Chen

The multinomial logistic regression (MLR) model is widely used in statistics and machine learning. Stochastic gradient descent (SGD) is the most common approach for determining the parameters of a MLR model in big data scenarios. However,…

Optimization and Control · Mathematics 2021-05-03 Borja Sánchez-López , Jesus Cerquides

Neural networks are usually trained by some form of stochastic gradient descent (SGD)). A number of strategies are in common use intended to improve SGD optimization, such as learning rate schedules, momentum, and batching. These are…

Neural and Evolutionary Computing · Computer Science 2015-08-13 Thomas M. Breuel