English
Related papers

Related papers: Implicit differentiation with second-order derivat…

200 papers

In this paper we consider a nonconvex unconstrained optimization problem minimizing a twice differentiable objective function with H\"older continuous Hessian. Specifically, we first propose a Newton-conjugate gradient (Newton-CG) method…

Optimization and Control · Mathematics 2025-04-15 Chuan He , Heng Huang , Zhaosong Lu

Several machine learning applications involve the optimization of higher-order derivatives (e.g., gradients of gradients) during training, which can be expensive in respect to memory and computation even with automatic differentiation. As a…

Machine Learning · Computer Science 2020-11-26 Tianyu Pang , Kun Xu , Chongxuan Li , Yang Song , Stefano Ermon , Jun Zhu

Due to the effectiveness of second-order algorithms in solving classical optimization problems, designing second-order optimizers to train deep neural networks (DNNs) has attracted much research interest in recent years. However, because of…

Machine Learning · Computer Science 2024-03-06 Ying Sun , Hongwei Yong , Lei Zhang

This letter presents a method to reduce the computational demands of including second-order dynamics sensitivity information into the Differential Dynamic Programming (DDP) trajectory optimization algorithm. An approach to DDP is developed…

Robotics · Computer Science 2022-07-01 John N. Nganga , Patrick M. Wensing

Deep learning algorithms often require solving a highly non-linear and nonconvex unconstrained optimization problem. Methods for solving optimization problems in large-scale machine learning, such as deep learning and deep reinforcement…

Machine Learning · Computer Science 2019-09-06 Jacob Rafati , Roummel F. Marcia

We demonstrate that automatic differentiation (AD), which has become commonly available in machine learning frameworks, is an efficient way to explore ideas that lead to algorithmic improvement in multi-scale affine image registration and…

Optimization and Control · Mathematics 2025-08-05 Warin Watson , Cash Cherry , Rachelle Lang

The essential difficulty of gradient-based bilevel optimization using implicit differentiation is to estimate the inverse Hessian vector product with respect to neural network parameters. This paper proposes to tackle this problem by the…

Machine Learning · Computer Science 2023-02-21 Ryuichiro Hataya , Makoto Yamada

We present a GPU-based system for automatic differentiation (AD) of functions defined on triangle meshes, designed to exploit the locality and sparsity in mesh-based computation. Our system evaluates derivatives using per-element…

Graphics · Computer Science 2026-02-03 Ahmed H. Mahmoud , Rahul Goel , Jonathan Ragan-Kelley , Justin Solomon

We study online inference and asymptotic covariance estimation for the stochastic gradient descent (SGD) algorithm. While classical methods (such as plug-in and batch-means estimators) are available, they either require inaccessible…

Machine Learning · Statistics 2026-04-24 Ziyang Wei , Wanrong Zhu , Jingyang Lyu , Wei Biao Wu

Quasi-Newton methods form an important class of methods for solving nonlinear optimization problems. In such methods, first order information is used to approximate the second derivative. The aim is to mimic the fast convergence that can be…

Optimization and Control · Mathematics 2025-02-20 Aban Ansari-Önnestam , Anders Forsgren

First-order optimization algorithms can be considered as a discretization of ordinary differential equations (ODEs) \cite{su2014differential}. In this perspective, studying the properties of the corresponding trajectories may lead to…

Optimization and Control · Mathematics 2022-06-22 Jean-François Aujol , Charles Dossal , Văn Hào Hoàng , Hippolyte Labarrière , Aude Rondepierre

Multi-task learning through composite loss functions is fundamental to modern deep learning, yet optimizing competing objectives remains challenging. We present new theoretical and practical approaches for addressing directional conflicts…

Machine Learning · Computer Science 2025-09-22 Sifan Wang , Ananyae Kumar Bhartari , Bowen Li , Paris Perdikaris

We consider a scalar function depending on a numerical solution of an initial value problem, and its second-derivative (Hessian) matrix for the initial value. The need to extract the information of the Hessian or to solve a linear system…

Numerical Analysis · Mathematics 2020-07-09 Shin-ichi Ito , Takeru Matsuda , Yuto Miyatake

Discrete gradient methods are a class of numerical integrators producing solutions with exact preservation of first integrals of ordinary differential equations. In this paper, we apply order theory combined with the symmetrized Itoh--Abe…

Numerical Analysis · Mathematics 2026-01-13 Håkon Noren Myhr , Sølve Eidnes

Differentiable programming, enabled by automatic differentiation (AD), provides a robust framework for gradient-based optimization in computational plasma physics. While optimization is often only used towards design, we demonstrate that it…

Plasma Physics · Physics 2026-03-13 A. S. Joglekar , A. G. R. Thomas , A. L. Milder , K. G. Miller , J. P. Palastro , D. H. Froula

Physics-informed machine learning and inverse modeling require the solution of ill-conditioned non-convex optimization problems. First-order methods, such as SGD and ADAM, and quasi-Newton methods, such as BFGS and L-BFGS, have been applied…

Numerical Analysis · Mathematics 2021-05-18 Kailai Xu , Eric Darve

We aim at computing the derivative of the solution to a parametric optimization problem with respect to the involved parameters. For a class broader than that of strongly convex functions, this can be achieved by automatic differentiation…

Optimization and Control · Mathematics 2019-10-15 Sheheryar Mehmood , Peter Ochs

We introduce ADAHESSIAN, a second order stochastic optimization algorithm which dynamically incorporates the curvature of the loss function via ADAptive estimates of the HESSIAN. Second order algorithms are among the most powerful…

Machine Learning · Computer Science 2021-04-30 Zhewei Yao , Amir Gholami , Sheng Shen , Mustafa Mustafa , Kurt Keutzer , Michael W. Mahoney

For training fully-connected neural networks (FCNNs), we propose a practical approximate second-order method including: 1) an approximation of the Hessian matrix and 2) a conjugate gradient (CG) based method. Our proposed approximate…

Machine Learning · Computer Science 2018-12-07 Sheng-Wei Chen , Chun-Nan Chou , Edward Y. Chang

Stochastic gradients for deep neural networks exhibit strong correlations along the optimization trajectory, and are often aligned with a small set of Hessian eigenvectors associated with outlier eigenvalues. Recent work shows that…

Machine Learning · Computer Science 2026-02-04 Julien Nicolas , Mohamed Maouche , Sonia Ben Mokhtar , Mark Coates