English
Related papers

Related papers: Parabolic Approximation Line Search for DNNs

200 papers

While traditional Deep Learning (DL) optimization methods treat all training samples equally, Distributionally Robust Optimization (DRO) adaptively assigns importance weights to different samples. However, a significant gap exists between…

Achieving robust uncertainty quantification for deep neural networks represents an important requirement in many real-world applications of deep learning such as medical imaging where it is necessary to assess the reliability of a neural…

Machine Learning · Computer Science 2024-03-15 Tim Rensmeyer , Oliver Niggemann

We address the challenge of optimizing meta-parameters (hyperparameters) in machine learning, a key factor for efficient training and high model performance. Rather than relying on expensive meta-parameter search methods, we introduce…

Machine Learning · Computer Science 2025-07-10 Arsalan Sharifnassab , Saber Salehkaleybar , Richard Sutton

With increasing scale in model and dataset size, the training of deep neural networks becomes a massive computational burden. One approach to speed up the training process is Selective Backprop. For this approach, we perform a forward pass…

Machine Learning · Computer Science 2023-12-11 Lukas Balles , Cedric Archambeau , Giovanni Zappella

The linear primal-dual hybrid gradient (PDHG) method is a first-order method that splits convex optimization problems with saddle-point structure into smaller subproblems. Unlike those obtained in most splitting methods, these subproblems…

Optimization and Control · Mathematics 2022-04-05 Jérôme Darbon , Gabriel P. Langlois

Training a neural network with the gradient descent algorithm gives rise to a discrete-time nonlinear dynamical system. Consequently, behaviors that are typically observed in these systems emerge during training, such as convergence to an…

Machine Learning · Computer Science 2018-10-10 Kamil Nar , S. Shankar Sastry

Recent progress in deep learning has been driven by increasingly larger models. However, their computational and energy demands have grown proportionally, creating significant barriers to their deployment and to a wider adoption of deep…

Machine Learning · Computer Science 2025-09-16 Pedro Savarese

Iterative methods such as iterative closest point (ICP) for point cloud registration often suffer from bad local optimality (e.g. saddle points), due to the nature of nonconvex optimization. To address this fundamental challenge, in this…

Computer Vision and Pattern Recognition · Computer Science 2024-11-19 Ziming Zhang , Yuping Shao , Yiqing Zhang , Fangzhou Lin , Haichong Zhang , Elke Rundensteiner

Data augmentation has been an indispensable tool to improve the performance of deep neural networks, however the augmentation can hardly transfer among different tasks and datasets. Consequently, a recent trend is to adopt AutoML technique…

Computer Vision and Pattern Recognition · Computer Science 2021-10-13 Aoming Liu , Zehao Huang , Zhiwu Huang , Naiyan Wang

Deep neural networks are commonly trained using stochastic non-convex optimization procedures, which are driven by gradient information estimated on fractions (batches) of the dataset. While it is commonly accepted that batch size is an…

Machine Learning · Computer Science 2016-04-26 Ilya Loshchilov , Frank Hutter

This paper considers unconstrained convex optimization problems with time-varying objective functions. We propose algorithms with a discrete time-sampling scheme to find and track the solution trajectory based on prediction and correction…

Information Theory · Computer Science 2017-09-18 Andrea Simonetto , Aryan Mokhtari , Alec Koppel , Geert Leus , Alejandro Ribeiro

Adaptive regularized framework using cubics has emerged as an alternative to line-search and trust-region algorithms for smooth nonconvex optimization, with an optimal complexity amongst second-order methods. In this paper, we propose and…

Optimization and Control · Mathematics 2018-05-30 El houcine Bergou , Youssef Diouane , Serge Gratton

Neural architecture search (NAS) typically consists of three main steps: training a super-network, training and evaluating sampled deep neural networks (DNNs), and training the discovered DNN. Most of the existing efforts speed up some…

Computer Vision and Pattern Recognition · Computer Science 2021-04-02 Tien-Ju Yang , Yi-Lun Liao , Vivienne Sze

In recent years, there has been a growing interest in leveraging deep learning and neural networks to address scientific problems, particularly in solving partial differential equations (PDEs). However, many neural network-based methods…

Machine Learning · Computer Science 2024-04-24 Adrian Celaya , Keegan Kirk , David Fuentes , Beatrice Riviere

In robotics, deep learning (DL) methods are used more and more widely, but their general inability to provide reliable confidence estimates will ultimately lead to fragile and unreliable systems. This impedes the potential deployments of DL…

Robotics · Computer Science 2020-11-02 Matthias Humt , Jongseok Lee , Rudolph Triebel

Models for multiphysics problems often contain strong nonlinearities. Including fracture contact mechanics introduces discontinuities at the transition between open and closed or sliding and sticking fractures. The resulting system of…

Numerical Analysis · Mathematics 2024-07-02 Ivar Stefansson

We consider descent methods for solving non-finite valued nonsmooth convex-composite optimization problems that employ Gauss-Newton subproblems to determine the iteration update. Specifically, we establish the global convergence properties…

Optimization and Control · Mathematics 2019-09-11 James V. Burke , Abraham Engle

Hyperparameters greatly impact models' capabilities; however, modern models are too large for extensive search. Instead, researchers design recipes that train well across scales based on their understanding of the hyperparameters. Despite…

Machine Learning · Computer Science 2025-10-06 Nicholas Lourie , He He , Kyunghyun Cho

Extending Bayesian optimization to batch evaluation can enable the designer to make the most use of parallel computing technology. However, most of current batch approaches do not scale well with the batch size. That is, their performances…

Machine Learning · Computer Science 2025-04-25 Dawei Zhan , Zhaoxi Zeng , Shuoxiao Wei , Ping Wu

Consider composite nonconvex optimization problems where the objective function consists of a smooth nonconvex term (with Lipschitz-continuous gradient) and a convex (possibly nonsmooth) term. Existing parameter-free methods for such…

Optimization and Control · Mathematics 2025-10-08 Zilong Ye , Shiqian Ma , Junfeng Yang , Danqing Zhou