English
Related papers

Related papers: Ginger: An Efficient Curvature Approximation with …

200 papers

Second-order optimization algorithms exhibit excellent convergence properties for training deep learning models, but often incur significant computation and memory overheads. This can result in lower training efficiency than the first-order…

Machine Learning · Computer Science 2023-08-07 Lin Zhang , Shaohuai Shi , Bo Li

We introduce a fast algorithm for entry-wise evaluation of the Gauss-Newton Hessian (GNH) matrix for the fully-connected feed-forward neural network. The algorithm has a precomputation step and a sampling step. While it generally requires…

Numerical Analysis · Mathematics 2020-11-17 Chao Chen , Severin Reiz , Chenhan Yu , Hans-Joachim Bungartz , George Biros

Successive quadratic approximations, or second-order proximal methods, are useful for minimizing functions that are a sum of a smooth part and a convex, possibly nonsmooth part that promotes regularization. Most analyses of iteration…

Optimization and Control · Mathematics 2019-01-25 Ching-pei Lee , Stephen J. Wright

In recent years, Graph Neural Networks (GNNs) have been utilized for various applications ranging from drug discovery to network design and social networks. In many applications, it is impossible to observe some properties of the graph…

Machine Learning · Computer Science 2025-03-12 Moshe Eliasof , Md Shahriar Rahim Siddiqui , Carola-Bibiane Schönlieb , Eldad Haber

To edit a real photo using Generative Adversarial Networks (GANs), we need a GAN inversion algorithm to identify the latent vector that perfectly reproduces it. Unfortunately, whereas existing inversion algorithms can synthesize images…

Computer Vision and Pattern Recognition · Computer Science 2022-02-25 Qianli Feng , Viraj Shah , Raghudeep Gadde , Pietro Perona , Aleix Martinez

In this paper, we consider stochastic second-order methods for minimizing a finite summation of nonconvex functions. One important key is to find an ingenious but cheap scheme to incorporate local curvature information. Since the true…

Optimization and Control · Mathematics 2021-03-26 Minghan Yang , Dong Xu , Hongyu Chen , Zaiwen Wen , Mengyun Chen

For numerous parameter and state estimation problems, assimilating new data as they become available can help produce accurate and fast inference of unknown quantities. While most existing algorithms for solving those kind of ill-posed…

Numerical Analysis · Mathematics 2022-07-28 Neil K. Chada , Marco A. Iglesias , Shuai Lu , Frank Werner

Despite recent progress in time-series foundation models, challenges persist in improving representation learning and adapting to diverse downstream tasks. We introduce a General Time-series Model (GTM), which advances representation…

Machine Learning · Computer Science 2026-03-13 Cheng He , Xu Huang , Gangwei Jiang , Zhaoyi Li , Defu Lian , Hong Xie , Enhong Chen , Xijie Liang , Zengrong Zheng , Patrick P. C. Lee

In this work, we establish non-asymptotic convergence bounds for the Gauss-Newton method in training neural networks with smooth activations. In the underparameterized regime, the Gauss-Newton gradient flow in parameter space induces a…

Optimization and Control · Mathematics 2025-12-23 Semih Cayci

We conjecture that the inherent difference in generalisation between adaptive and non-adaptive gradient methods in deep learning stems from the increased estimation noise in the flattest directions of the true loss surface. We demonstrate…

Machine Learning · Statistics 2022-03-17 Diego Granziol , Nicholas Baskerville

Maximum entropy inference and learning of graphical models are pivotal tasks in learning theory and optimization. This work extends algorithms for these problems, including generalized iterative scaling (GIS) and gradient descent (GD), to…

Machine Learning · Computer Science 2024-07-17 Minbo Gao , Zhengfeng Ji , Fuchao Wei

In the context of over-parameterization, there is a line of work demonstrating that randomly initialized (stochastic) gradient descent (GD) converges to a globally optimal solution at a linear convergence rate for the quadratic loss…

Machine Learning · Computer Science 2025-06-16 Xianliang Xu , Ting Du , Wang Kong , Bin Shan , Ye Li , Zhongyi Huang

Solving complex optimization problems in engineering and the physical sciences requires repetitive computation of multi-dimensional function derivatives. Commonly, this requires computationally-demanding numerical differentiation such as…

Numerical Analysis · Mathematics 2021-05-12 Danny Smyl , Tyler N. Tallman , Dong Liu , Andreas Hauptmann

We propose an inexact variable-metric proximal point algorithm to accelerate gradient-based optimization algorithms. The proposed scheme, called QNing can be notably applied to incremental first-order methods such as the stochastic…

Machine Learning · Statistics 2019-01-30 Hongzhou Lin , Julien Mairal , Zaid Harchaoui

Neural networks are a powerful class of non-linear functions. However, their black-box nature makes it difficult to explain their behaviour and certify their safety. Abstraction techniques address this challenge by transforming the neural…

Machine Learning · Computer Science 2023-04-03 Edoardo Manino , Iury Bessa , Lucas Cordeiro

In this thesis, we disentangle the generalized Gauss-Newton and approximate inference for Bayesian deep learning. The generalized Gauss-Newton method is an optimization method that is used in several popular Bayesian deep learning…

Machine Learning · Statistics 2020-07-24 Alexander Immer

We introduce Natural Neural Networks, a novel family of algorithms that speed up convergence by adapting their internal representation during training to improve conditioning of the Fisher matrix. In particular, we show a specific example…

Machine Learning · Statistics 2015-07-02 Guillaume Desjardins , Karen Simonyan , Razvan Pascanu , Koray Kavukcuoglu

Second-order methods such as KFAC can be useful for neural net training. However, they are often memory-inefficient since their preconditioning Kronecker factors are dense, and numerically unstable in low precision as they require matrix…

Machine Learning · Computer Science 2024-07-24 Wu Lin , Felix Dangel , Runa Eschenhagen , Kirill Neklyudov , Agustinus Kristiadi , Richard E. Turner , Alireza Makhzani

The state-of-the-art dimensionality reduction approaches largely rely on complicated optimization procedures. On the other hand, closed-form approaches requiring merely eigen-decomposition do not have enough sophistication and nonlinearity.…

Machine Learning · Computer Science 2023-08-14 Chengrui Li , Anqi Wu

Inverse problems are in many cases solved with optimization techniques. When the underlying model is linear, first-order gradient methods are usually sufficient. With nonlinear models, due to nonconvexity, one must often resort to…

Numerical Analysis · Mathematics 2023-05-15 Arttu Arjas , Mikko J. Sillanpää , Andreas Hauptmann
‹ Prev 1 3 4 5 6 7 10 Next ›