English
Related papers

Related papers: Partial local entropy and anisotropy in deep weigh…

200 papers

Adaptive loss function formulation is an active area of research and has gained a great deal of popularity in recent years, following the success of deep learning. However, existing frameworks of adaptive loss functions often suffer from…

Machine Learning · Computer Science 2020-01-01 A. Ali Heydari , Craig A. Thompson , Asif Mehmood

Recent empirical evidence has demonstrated that the training dynamics of large-scale deep neural networks occur within low-dimensional subspaces. While this has inspired new research into low-rank training, compression, and adaptation,…

Machine Learning · Computer Science 2026-02-09 Alec S. Xu , Can Yaras , Matthew Asato , Qing Qu , Laura Balzano

We introduce a tunable loss function called $\alpha$-loss, parameterized by $\alpha \in (0,\infty]$, which interpolates between the exponential loss ($\alpha = 1/2$), the log-loss ($\alpha = 1$), and the 0-1 loss ($\alpha = \infty$), for…

Machine Learning · Computer Science 2022-12-22 Tyler Sypherd , Mario Diaz , John Kevin Cava , Gautam Dasarathy , Peter Kairouz , Lalitha Sankar

We introduce two-scale loss functions for use in various gradient descent algorithms applied to classification problems via deep neural networks. This new method is generic in the sense that it can be applied to a wide range of machine…

Numerical Analysis · Mathematics 2021-09-03 Leonid Berlyand , Robert Creese , Pierre-Emmanuel Jabin

One of the central challenges in modern machine learning is understanding how neural networks generalize knowledge learned from training data to unseen test data. While numerous empirical techniques have been proposed to improve…

Machine Learning · Computer Science 2025-04-18 Entao Yang , Xiaotian Zhang , Yue Shang , Ge Zhang

In many computer vision tasks, for example saliency prediction or semantic segmentation, the desired output is a foreground map that predicts pixels where some criteria is satisfied. Despite the inherently spatial nature of this task…

Computer Vision and Pattern Recognition · Computer Science 2017-08-08 Nicholas Kolkin , Gregory Shakhnarovich , Eli Shechtman

This paper studies some asymptotic properties of adaptive algorithms widely used in optimization and machine learning, and among them Adagrad and Rmsprop, which are involved in most of the blackbox deep learning algorithms. Our setup is the…

Machine Learning · Statistics 2020-12-15 Sébastien Gadat , Ioana Gavra

In this paper, a new asymptotic preserving (AP) scheme is proposed for the anisotropic elliptic equations. Different from previous AP schemes, the actual one is based on first-order system least-squares for second-order partial differential…

Numerical Analysis · Mathematics 2022-02-09 Long Li , Chang Yang

Significant advances have been made recently on training neural networks, where the main challenge is in solving an optimization problem with abundant critical points. However, existing approaches to address this issue crucially rely on a…

Machine Learning · Computer Science 2019-02-28 Weihao Gao , Ashok Vardhan Makkuva , Sewoong Oh , Pramod Viswanath

Existing classification-based face recognition methods have achieved remarkable progress, introducing large margin into hypersphere manifold to learn discriminative facial representations. However, the feature distribution is ignored. Poor…

Computer Vision and Pattern Recognition · Computer Science 2021-07-08 Chengzhi Jiang , Yanzhou Su , Wen Wang , Haiwei Bai , Haijun Liu , Jian Cheng

We introduce "AnnealSGD", a regularized stochastic gradient descent algorithm motivated by an analysis of the energy landscape of a particular class of deep networks with sparse random weights. The loss function of such networks can be…

Machine Learning · Computer Science 2017-04-25 Pratik Chaudhari , Stefano Soatto

Deep Metric Learning (DML) loss functions traditionally aim to control the forces of separability and compactness within an embedding space so that the same class data points are pulled together and different class ones are pushed apart.…

Computer Vision and Pattern Recognition · Computer Science 2024-09-04 Michael G. DeMoor , John J. Prevost

We prove linear convergence of gradient descent to a global optimum for the training of deep residual networks with constant layer width and smooth activation function. We show that if the trained weights, as a function of the layer index,…

Machine Learning · Computer Science 2023-01-26 Rama Cont , Alain Rossier , RenYuan Xu

We investigate the topics of sensitivity and robustness in feedforward and convolutional neural networks. Combining energy landscape techniques developed in computational chemistry with tools drawn from formal methods, we produce empirical…

Machine Learning · Statistics 2018-12-06 Timothy E. Wang , Yiming Gu , Dhagash Mehta , Xiaojun Zhao , Edgar A. Bernal

The entropy of the codes usually serves as the rate loss in the recent learned lossy image compression methods. Precise estimation of the probabilistic distribution of the codes plays a vital role in the performance. However, existing deep…

Image and Video Processing · Electrical Eng. & Systems 2020-05-12 Mu Li , Kai Zhang , Wangmeng Zuo , Radu Timofte , David Zhang

The leading approach for image compression with artificial neural networks (ANNs) is to learn a nonlinear transform and a fixed entropy model that are optimized for rate-distortion performance. We show that this approach can be…

Computer Vision and Pattern Recognition · Computer Science 2018-06-01 David Minnen , George Toderici , Saurabh Singh , Sung Jin Hwang , Michele Covell

We consider the approximation of functions by 2-layer neural networks with a small number of hidden weights based on the squared loss and small datasets. Due to the highly non-convex energy landscape, gradient-based training often suffers…

Machine Learning · Computer Science 2025-08-14 Johannes Hertrich , Sebastian Neumayer

The role of $L^2$ regularization, in the specific case of deep neural networks rather than more traditional machine learning models, is still not fully elucidated. We hypothesize that this complex interplay is due to the combination of…

Machine Learning · Computer Science 2019-02-11 Pierre H. Richemond , Yike Guo

Objective functions that optimize deep neural networks play a vital role in creating an enhanced feature representation of the input data. Although cross-entropy-based loss formulations have been extensively used in a variety of supervised…

Computer Vision and Pattern Recognition · Computer Science 2023-12-19 Deen Dayal Mohan , Bhavin Jawade , Srirangaraj Setlur , Venu Govindaraj

One of the most important parts of Artificial Neural Networks is minimizing the loss functions which tells us how good or bad our model is. To minimize these losses we need to tune the weights and biases. Also to calculate the minimum value…

Machine Learning · Computer Science 2021-01-08 Kaustubh Yadav