English
Related papers

Related papers: Implicit differentiation with second-order derivat…

200 papers

Pre-conditioning is a well-known concept that can significantly improve the convergence of optimization algorithms. For noise-free problems, where good pre-conditioners are not known a priori, iterative linear algebra methods offer one way…

Machine Learning · Computer Science 2019-02-21 Filip de Roos , Philipp Hennig

This paper presents a novel natural gradient and Hessian-free (NGHF) optimisation framework for neural network training that can operate efficiently in a distributed manner. It relies on the linear conjugate gradient (CG) algorithm to…

Machine Learning · Computer Science 2021-03-16 Adnan Haider , Chao Zhang , Florian L. Kreyssig , Philip C. Woodland

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

Natural Gradient Descent, a second-degree optimization method motivated by the information geometry, makes use of the Fisher Information Matrix instead of the Hessian which is typically used. However, in many cases, the Fisher Information…

Machine Learning · Computer Science 2023-03-10 Rajesh Shrestha

We present PYHESSIAN, a new scalable framework that enables fast computation of Hessian (i.e., second-order derivative) information for deep neural networks. PYHESSIAN enables fast computations of the top Hessian eigenvalues, the Hessian…

Machine Learning · Computer Science 2021-04-21 Zhewei Yao , Amir Gholami , Kurt Keutzer , Michael Mahoney

Derivative-based algorithms are ubiquitous in statistics, machine learning, and applied mathematics. Automatic differentiation offers an algorithmic way to efficiently evaluate these derivatives from computer programs that execute relevant…

Computation · Statistics 2022-03-01 Charles C. Margossian , Michael Betancourt

Neural implicit representation is a promising approach for reconstructing surfaces from point clouds. Existing methods combine various regularization terms, such as the Eikonal and Laplacian energy terms, to enforce the learned neural…

Computer Vision and Pattern Recognition · Computer Science 2023-09-07 Zixiong Wang , Yunxiao Zhang , Rui Xu , Fan Zhang , Pengshuai Wang , Shuangmin Chen , Shiqing Xin , Wenping Wang , Changhe Tu

Bilevel optimization, addressing challenges in hierarchical learning tasks, has gained significant interest in machine learning. The practical implementation of the gradient descent method to bilevel optimization encounters computational…

Machine Learning · Computer Science 2025-02-04 Sheng Fang , Yong-Jin Liu , Wei Yao , Chengming Yu , Jin Zhang

Bilevel optimization has arisen as a powerful tool in modern machine learning. However, due to the nested structure of bilevel optimization, even gradient-based methods require second-order derivative approximations via Jacobian- or/and…

Machine Learning · Computer Science 2022-06-07 Daouda Sow , Kaiyi Ji , Yingbin Liang

We present an algorithm for minimizing a sum of functions that combines the computational efficiency of stochastic gradient descent (SGD) with the second order curvature information leveraged by quasi-Newton methods. We unify these…

Machine Learning · Computer Science 2014-12-02 Jascha Sohl-Dickstein , Ben Poole , Surya Ganguli

Implicit bias induced by gradient-based algorithms is essential to the generalization of overparameterized models, yet its mechanisms can be subtle. This work leverages the Normalized Steepest Descent} (NSD) framework to investigate how…

Machine Learning · Computer Science 2026-03-25 Shengping Xie , Zekun Wu , Quan Chen , Kaixu Tang

First-order variational equations are widely used in N-body simulations to study how nearby trajectories diverge from one another. These allow for efficient and reliable determinations of chaos indicators such as the Maximal Lyapunov…

Earth and Planetary Astrophysics · Physics 2016-03-23 Hanno Rein , Daniel Tamayo

Meta-learning that uses implicit gradient have provided an exciting alternative to standard techniques which depend on the trajectory of the inner loop training. Implicit meta-learning (IML), however, require computing $2^{nd}$ order…

Machine Learning · Computer Science 2023-10-31 Fady Rezk

Time-dependent Partial Differential Equations with given initial conditions are considered in this paper. New differentiation techniques of the unknown solution with respect to time variable are proposed. It is shown that the proposed…

Numerical Analysis · Mathematics 2022-10-24 Marat S. Mukhametzhanov

Affine normal directions provide intrinsic affine-invariant descent directions derived from the geometry of level sets. Their practical use, however, has long been hindered by the need to evaluate third-order derivatives and invert tangent…

Optimization and Control · Mathematics 2026-04-02 Yi-Shuai Niu , Artan Sheshmani , Shing-Tung Yau

Optimization of beamlines and lattices is a common problem in accelerator physics, which is usually solved with semi-analytical methods and numerical optimization routines. However, these are usually of the gradient-free or…

Accelerator Physics · Physics 2025-07-14 Francisco Huhn , Francesco M. Velotti

We propose a novel second-order optimization framework for training the emerging deep continuous-time models, specifically the Neural Ordinary Differential Equations (Neural ODEs). Since their training already involves expensive gradient…

Machine Learning · Computer Science 2021-11-09 Guan-Horng Liu , Tianrong Chen , Evangelos A. Theodorou

We present a novel approach to accelerate stochastic gradient descent (SGD) by utilizing curvature information obtained from Hessian-vector products or finite differences of parameters and gradients, similar to the BFGS algorithm. Our…

Machine Learning · Computer Science 2024-02-08 Omead Pooladzandi , Xi-Lin Li

We consider minimization of a smooth nonconvex objective function using an iterative algorithm based on Newton's method and the linear conjugate gradient algorithm, with explicit detection and use of negative curvature directions for the…

Optimization and Control · Mathematics 2018-11-14 Clément W. Royer , Michael O'Neill , Stephen J. Wright

This paper proposes a novel preconditioned implicit-explicit algorithm enhanced with the extrapolation technique for non-convex optimization problems. The algorithm employs a third-order Adams-Bashforth scheme for the nonlinear and explicit…

Optimization and Control · Mathematics 2025-09-19 Kelin Wu , Hongpeng Sun
‹ Prev 1 4 5 6 7 8 10 Next ›