English
Related papers

Related papers: One-step differentiation of iterative algorithms

200 papers

Scientific studies often require the precise calculation of derivatives. In many cases an analytical calculation is not feasible and one resorts to evaluating derivatives numerically. These are error-prone, especially for higher-order…

High Energy Physics - Phenomenology · Physics 2010-05-28 Mathias Wagner , Andrea Walther , Bernd-Jochen Schaefer

We study a general class of bilevel problems, consisting in the minimization of an upper-level objective which depends on the solution to a parametric fixed-point equation. Important instances arising in machine learning include…

Machine Learning · Statistics 2020-07-13 Riccardo Grazzi , Luca Franceschi , Massimiliano Pontil , Saverio Salzo

In recent years, implicit deep learning has emerged as a method to increase the effective depth of deep neural networks. While their training is memory-efficient, they are still significantly slower to train than their explicit…

Machine Learning · Computer Science 2023-03-13 Zaccharie Ramzi , Florian Mannel , Shaojie Bai , Jean-Luc Starck , Philippe Ciuciu , Thomas Moreau

We propose a one-step procedure to estimate the latent positions in random dot product graphs efficiently. Unlike the classical spectral-based methods such as the adjacency and Laplacian spectral embedding, the proposed one-step procedure…

Statistics Theory · Mathematics 2020-11-16 Fangzheng Xie , Yanxun Xu

Recent advances in one-shot imitation learning have enabled robots to acquire new manipulation skills from a single human demonstration. While existing methods achieve strong performance on single-step tasks, they remain limited in their…

Robotics · Computer Science 2025-09-30 Vijja Wichitwechkarn , Emlyn Williams , Charles Fox , Ruchi Choudhary

The present work deals with an improved back-propagation algorithm based on Gauss-Newton numerical optimization method for fast convergence. The steepest descent method is used for the back-propagation. The algorithm is tested using various…

Artificial Intelligence · Computer Science 2012-06-21 Sudarshan Nandy , Partha Pratim Sarkar , Achintya Das

In this pedagogical article, we present a simple direct matrix method for analytically computing the Jacobian of nonlinear algebraic equations that arise from the discretization of nonlinear integro-differential equations. The method is…

Numerical Analysis · Mathematics 2009-05-26 Kevin T. Chu

We study and derive algorithms for nonlinear eigenvalue problems, where the system matrix depends on the eigenvector, or several eigenvectors (or their corresponding invariant subspace). The algorithms are derived from an implicit…

Numerical Analysis · Mathematics 2020-03-02 Elias Jarlebring , Parikshit Upadhyaya

Computing the Jacobian of the solution of an optimization problem is a central problem in machine learning, with applications in hyperparameter optimization, meta-learning, optimization as a layer, and dataset distillation, to name a few.…

Optimization and Control · Mathematics 2023-08-28 Damien Scieur , Quentin Bertrand , Gauthier Gidel , Fabian Pedregosa

The study of Newton's method in complex-valued neural networks faces many difficulties. In this paper, we derive Newton's method backpropagation algorithms for complex-valued holomorphic multilayer perceptrons, and investigate the…

Complex Variables · Mathematics 2014-06-23 Diana Thomson La Corte , Yi Ming Zou

An algorithm is proposed for solving optimization problems with stochastic objective and deterministic equality and inequality constraints. This algorithm is objective-function-free in the sense that it only uses the objective's gradient…

Optimization and Control · Mathematics 2026-04-01 S. Gratton , Ph. L. Toint

Automatic differentiation is a key component in deep learning. This topic is well studied and excellent surveys such as Baydin et al. (2018) have been available to clearly describe the basic concepts. Further, sophisticated implementations…

Machine Learning · Computer Science 2024-12-18 Yu-Hsueh Fang , He-Zhe Lin , Jie-Jyun Liu , Chih-Jen Lin

The paradigm of differentiable programming has significantly enhanced the scope of machine learning via the judicious use of gradient-based optimization. However, standard differentiable programming methods (such as autodiff) typically…

In this paper, we introduce a new iterative method which we call one step back approach: the main idea is to anticipate the consequence of the iterative computation per coordinate and to optimize on the choice of the sequence of the…

Numerical Analysis · Computer Science 2013-02-19 Dohy Hong

We present a simplified computational rule for the back-propagation formulas for artificial neural networks. In this work, we provide a generic two-step rule for the back-propagation algorithm in matrix notation. Moreover, this rule…

Neural and Evolutionary Computing · Computer Science 2023-05-17 Ahmed Boughammoura

The proximal gradient algorithm has been popularly used for convex optimization. Recently, it has also been extended for nonconvex problems, and the current state-of-the-art is the nonmonotone accelerated proximal gradient algorithm.…

Optimization and Control · Mathematics 2017-05-24 Quanming Yao , James T. Kwok , Fei Gao , Wei Chen , Tie-Yan Liu

In view of training increasingly complex learning architectures, we establish a nonsmooth implicit function theorem with an operational calculus. Our result applies to most practical problems (i.e., definable problems) provided that a…

Machine Learning · Computer Science 2022-04-06 Jérôme Bolte , Tam Le , Edouard Pauwels , Antonio Silveti-Falls

Many optimization problems require balancing multiple conflicting objectives. As gradient descent is limited to single-objective optimization, we introduce its direct generalization: Jacobian descent (JD). This algorithm iteratively updates…

Machine Learning · Computer Science 2025-02-04 Pierre Quinton , Valérian Rey

We propose proximal backpropagation (ProxProp) as a novel algorithm that takes implicit instead of explicit gradient steps to update the network parameters during neural network training. Our algorithm is motivated by the step size…

Machine Learning · Computer Science 2018-02-21 Thomas Frerix , Thomas Möllenhoff , Michael Moeller , Daniel Cremers

First-order automatic differentiation is a ubiquitous tool across statistics, machine learning, and computer science. Higher-order implementations of automatic differentiation, however, have yet to realize the same utility. In this paper I…

Computation · Statistics 2019-01-01 Michael Betancourt