English
Related papers

Related papers: Deep-ICE: the first globally optimal algorithm for…

200 papers

When training neural networks with custom objectives, such as ranking losses and shortest-path losses, a common problem is that they are, per se, non-differentiable. A popular approach is to continuously relax the objectives to provide…

Machine Learning · Computer Science 2024-10-28 Felix Petersen , Christian Borgelt , Tobias Sutter , Hilde Kuehne , Oliver Deussen , Stefano Ermon

Optimization in machine learning, both theoretical and applied, is presently dominated by first-order gradient methods such as stochastic gradient descent. Second-order optimization methods, that involve second derivatives and/or second…

Machine Learning · Computer Science 2021-03-08 Rohan Anil , Vineet Gupta , Tomer Koren , Kevin Regan , Yoram Singer

Deep neural networks trained using a softmax layer at the top and the cross-entropy loss are ubiquitous tools for image classification. Yet, this does not naturally enforce intra-class similarity nor inter-class margin of the learned deep…

Computer Vision and Pattern Recognition · Computer Science 2017-12-06 José Lezama , Qiang Qiu , Pablo Musé , Guillermo Sapiro

This paper presents an experimental analysis about trade-offs in top-k classification accuracies on losses for deep leaning and proposal of a novel top-k loss. Commonly-used cross entropy (CE) is not guaranteed to optimize top-k prediction…

Machine Learning · Computer Science 2020-07-31 Azusa Sawada , Eiji Kaneko , Kazutoshi Sagi

In a groundbreaking work, Schmidt-Hieber (2020) proved the minimax optimality of deep neural networks with ReLu activation for least-square regression estimation over a large class of functions defined by composition. In this paper, we…

Machine Learning · Statistics 2025-06-12 Pierre Alquier , William Kengne

Solving mixed-integer optimization problems with embedded neural networks with ReLU activation functions is challenging. Big-M coefficients that arise in relaxing binary decisions related to these functions grow exponentially with the…

Optimization and Control · Mathematics 2025-02-06 Christoph Plate , Mirko Hahn , Alexander Klimek , Caroline Ganzer , Kai Sundmacher , Sebastian Sager

The empirical emergence of neural collapse -- a surprising symmetry in the feature representations of the training data in the penultimate layer of deep neural networks -- has spurred a line of theoretical research aimed at its…

Machine Learning · Computer Science 2025-05-22 Peter Súkeník , Christoph H. Lampert , Marco Mondelli

We consider the task of decentralized minimization of the sum of smooth strongly convex functions stored across the nodes of a network. For this problem, lower bounds on the number of gradient computations and the number of communication…

Optimization and Control · Mathematics 2020-11-16 Dmitry Kovalev , Adil Salim , Peter Richtárik

How to develop slim and accurate deep neural networks has become crucial for real- world applications, especially for those employed in embedded systems. Though previous work along this research line has shown some promising results, most…

Neural and Evolutionary Computing · Computer Science 2019-10-02 Xin Dong , Shangyu Chen , Sinno Jialin Pan

This work presents a machine learning approach to optimize the energy efficiency (EE) in a multi-cell wireless network. This optimization problem is non-convex and its global optimum is difficult to find. In the literature, either simple…

Signal Processing · Electrical Eng. & Systems 2023-12-18 Bile Peng , Karl-Ludwig Besser , Ramprasad Raghunath , Eduard A. Jorswieck

Set partitioning is a key component of many algorithms in machine learning, signal processing, and communications. In general, the problem of finding a partition that minimizes a given impurity (loss function) is NP-hard. As such, there…

Information Theory · Computer Science 2020-01-01 Thuan Nguyen , Thinh Nguyen

Deep networks have produced significant gains for various visual recognition problems, leading to high impact academic and commercial applications. Recent work in deep networks highlighted that it is easy to generate images that humans…

Computer Vision and Pattern Recognition · Computer Science 2015-11-20 Abhijit Bendale , Terrance Boult

We develop fast algorithms and robust software for convex optimization of two-layer neural networks with ReLU activation functions. Our work leverages a convex reformulation of the standard weight-decay penalized training problem as a set…

Machine Learning · Computer Science 2025-04-10 Aaron Mishkin , Arda Sahiner , Mert Pilanci

The paper aims to investigate relevant computational issues of deep neural network architectures with an eye to the interaction between the optimization algorithm and the classification performance. In particular, we aim to analyze the…

Optimization and Control · Mathematics 2024-05-06 Corrado Coppola , Lorenzo Papa , Marco Boresta , Irene Amerini , Laura Palagi

The paper provides global optimization algorithms for two particularly difficult nonconvex problems raised by hybrid system identification: switching linear regression and bounded-error estimation. While most works focus on local…

Machine Learning · Computer Science 2017-11-27 Fabien Lauer

Communication compression has become a key strategy to speed up distributed optimization. However, existing decentralized algorithms with compression mainly focus on compressing DGD-type algorithms. They are unsatisfactory in terms of…

Machine Learning · Computer Science 2021-03-22 Xiaorui Liu , Yao Li , Rongrong Wang , Jiliang Tang , Ming Yan

In this paper, we present two new communication-efficient methods for distributed minimization of an average of functions. The first algorithm is an inexact variant of the DANE algorithm that allows any local algorithm to return an…

Optimization and Control · Mathematics 2016-08-25 Sashank J. Reddi , Jakub Konečný , Peter Richtárik , Barnabás Póczós , Alex Smola

For one-hidden-layer ReLU networks, we prove that all differentiable local minima are global inside differentiable regions. We give the locations and losses of differentiable local minima, and show that these local minima can be isolated…

Machine Learning · Computer Science 2020-06-18 Bo Liu

We present a novel global compression framework for deep neural networks that automatically analyzes each layer to identify the optimal per-layer compression ratio, while simultaneously achieving the desired overall compression. Our…

Machine Learning · Computer Science 2021-11-22 Lucas Liebenwein , Alaa Maalouf , Oren Gal , Dan Feldman , Daniela Rus

Deep neural networks (DNNs) have provided brilliant performance across various tasks. However, this success often comes at the cost of unnecessarily large model sizes, high computational demands, and substantial memory footprints.…

Machine Learning · Computer Science 2025-11-26 Shaharyar Ahmed Khan Tareen , Filza Khan Tareen