English
Related papers

Related papers: Random Linear Projections Loss for Hyperplane-Base…

200 papers

Why do neural networks trained with large learning rates for a longer time often lead to better generalization? In this paper, we delve into this question by examining the relation between training and testing loss in neural networks.…

Machine Learning · Computer Science 2024-01-23 Yinuo Ren , Chao Ma , Lexing Ying

Typically, loss functions, regularization mechanisms and other important aspects of training parametric models are chosen heuristically from a limited set of options. In this paper, we take the first step towards automating this process,…

Neural policies have shown promise in solving vehicle routing problems due to their reduced reliance on handcrafted heuristics. However, current training paradigms suffer from a fundamental limitation: they primarily focus on next-node…

Machine Learning · Computer Science 2026-05-20 Xia Jiang , Yaoxin Wu , Yew-Soon Ong , Yingqian Zhang

In this paper, we propose a novel approach for implicit data representation to evaluate similarity of input data using a trained neural network. In contrast to the previous approach, which uses gradients for representation, we utilize only…

Machine Learning · Computer Science 2020-10-12 Alan Savushkin , Nikita Benkovich , Dmitry Golubev

Convolutional Neural Networks (CNNs) have achieved state-of-the-art performance in many computer vision tasks over the years. However, this comes at the cost of heavy computation and memory intensive network designs, suggesting potential…

Computer Vision and Pattern Recognition · Computer Science 2020-08-11 Kumara Kahatapitiya , Ranga Rodrigo

Large Language Models (LLMs) have shown promising results on various language and vision tasks. Recently, there has been growing interest in applying LLMs to graph-based tasks, particularly on Text-Attributed Graphs (TAGs). However, most…

Machine Learning · Computer Science 2024-06-10 Zhongmou He , Jing Zhu , Shengyi Qian , Joyce Chai , Danai Koutra

Neural networks have achieved remarkable success in many cognitive tasks. However, when they are trained sequentially on multiple tasks without access to old data, their performance on early tasks tend to drop significantly. This problem is…

Machine Learning · Computer Science 2021-02-10 Dong Yin , Mehrdad Farajtabar , Ang Li , Nir Levine , Alex Mott

In this study, we investigate how the updating of weights during forward operation and the computation of gradients during backpropagation impact the optimization process, training procedure, and overall performance of the neural network,…

Machine Learning · Computer Science 2024-07-10 Amir Noorizadegan , D. L. Young , Y. C. Hon , C. S. Chen

Understanding and evaluating the robustness of neural networks under adversarial settings is a subject of growing interest. Attacks proposed in the literature usually work with models trained to minimize cross-entropy loss and output…

Machine Learning · Computer Science 2020-03-09 Sean Saito , Sujoy Roy

Deep neural networks (DNNs) are efficient solvers for ill-posed problems and have been shown to outperform classical optimization techniques in several computational imaging problems. DNNs are trained by solving an optimization problem…

Image and Video Processing · Electrical Eng. & Systems 2019-06-14 Mo Deng , Alexandre Goy , Shuai Li , Kwabena Arthur , George Barbastathis

In machine learning and statistical modeling, the mean square or absolute error is commonly used as an error metric, also called a "loss function." While effective in reducing the average error, this approach may fail to address localized…

Optimization and Control · Mathematics 2025-09-10 John M. Hanna , Hugues Talbot , Irene E. Vignon-Clementel

Path loss modeling is a widely used technique for estimating point-to-point losses along a communications link from transmitter (Tx) to receiver (Rx). Accurate path loss predictions can optimize use of the radio frequency spectrum and…

Machine Learning · Computer Science 2026-02-05 Ryan G. Dempsey , Jonathan Ethier , Halim Yanikomeroglu

Humans can often quickly and efficiently solve complex new learning tasks given only a small set of examples. In contrast, modern artificially intelligent systems often require thousands or millions of observations in order to solve even…

Machine Learning · Computer Science 2025-05-08 Christian Raymond

Linear Regression and neural networks are widely used to model data. Neural networks distinguish themselves from linear regression with their use of activation functions that enable modeling nonlinear functions. The standard argument for…

Machine Learning · Computer Science 2024-01-02 Anish Lakkapragada

Neural networks are becoming central in several areas of computer vision and image processing and different architectures have been proposed to solve specific problems. The impact of the loss layer of neural networks, however, has not…

Computer Vision and Pattern Recognition · Computer Science 2018-04-24 Hang Zhao , Orazio Gallo , Iuri Frosio , Jan Kautz

Neural networks have been successfully employed in various domains such as classification, regression and clustering, etc. Generally, the back propagation (BP) based iterative approaches are used to train the neural networks, however, it…

Neural and Evolutionary Computing · Computer Science 2023-06-23 A. K. Malik , Ruobin Gao , M. A. Ganaie , M. Tanveer , P. N. Suganthan

Despite their impressive performance, Deep Neural Networks (DNNs) typically underperform Gradient Boosting Trees (GBTs) on many tabular-dataset learning tasks. We propose that applying a different regularization coefficient to each weight…

Machine Learning · Statistics 2018-10-25 Ira Shavitt , Eran Segal

There is growing evidence that converting targets to soft targets in supervised learning can provide considerable gains in performance. Much of this work has considered classification, converting hard zero-one values to soft labels---such…

Machine Learning · Statistics 2018-06-13 Ehsan Imani , Martha White

We introduce a new algorithm, Regression based Supervised Learning (RSL), for learning per instance Neural Network (NN) defined heuristic functions for classical planning problems. RSL uses regression to select relevant sets of states at a…

Artificial Intelligence · Computer Science 2022-07-08 Stefan O'Toole , Miquel Ramirez , Nir Lipovetzky , Adrian R. Pearce

We explore unique considerations involved in fitting ML models to data with very high precision, as is often required for science applications. We empirically compare various function approximation methods and study how they scale with…

Machine Learning · Computer Science 2023-02-01 Eric J. Michaud , Ziming Liu , Max Tegmark