English
Related papers

Related papers: Practical Quasi-Newton Methods for Training Deep N…

200 papers

Deep artificial neural networks (DNNs) are typically trained via gradient-based learning algorithms, namely backpropagation. Evolution strategies (ES) can rival backprop-based algorithms such as Q-learning and policy gradients on…

Neural and Evolutionary Computing · Computer Science 2018-04-24 Felipe Petroski Such , Vashisht Madhavan , Edoardo Conti , Joel Lehman , Kenneth O. Stanley , Jeff Clune

Laplace approximation (LA) and its linearized variant (LLA) enable effortless adaptation of pretrained deep neural networks to Bayesian neural networks. The generalized Gauss-Newton (GGN) approximation is typically introduced to improve…

Machine Learning · Computer Science 2022-10-25 Zhijie Deng , Feng Zhou , Jun Zhu

This paper addresses the problem of optimizing partition functions in a stochastic learning setting. We propose a stochastic variant of the bound majorization algorithm that relies on upper-bounding the partition function with a quadratic…

Machine Learning · Computer Science 2020-11-04 Jing Wang , Anna Choromanska

In this paper, a modified BFGS algorithm is proposed. The modified BFGS matrix estimates a modified Hessian matrix which is a convex combination of an identity matrix for the steepest descent algorithm and a Hessian matrix for the Newton…

Optimization and Control · Mathematics 2025-11-14 Yaguang Yang

While offering a principled framework for uncertainty quantification in deep learning, the employment of Bayesian Neural Networks (BNNs) is still constrained by their increased computational requirements and the convergence difficulties…

Machine Learning · Computer Science 2025-05-26 Moule Lin , Shuhao Guan , Weipeng Jing , Goetz Botterweck , Andrea Patane

In this work, we propose Natural Hypergradient Descent (NHGD), a new method for solving bilevel optimization problems. To address the computational bottleneck in hypergradient estimation--namely, the need to compute or approximate Hessian…

Machine Learning · Computer Science 2026-04-02 Deyi Kong , Zaiwei Chen , Shuzhong Zhang , Shancong Mou

This paper develops a randomized approach for incrementally building deep neural networks, where a supervisory mechanism is proposed to constrain the random assignment of the weights and biases, and all the hidden layers have direct links…

Machine Learning · Computer Science 2018-03-19 Dianhui Wang , Ming Li

Stochastic gradient methods for minimizing nonconvex composite objective functions typically rely on the Lipschitz smoothness of the differentiable part, but this assumption fails in many important problem classes like quadratic inverse…

Optimization and Control · Mathematics 2025-01-22 Kuangyu Ding , Jingyang Li , Kim-Chuan Toh

We consider the problem of how to learn a step-size policy for the Limited-Memory Broyden-Fletcher-Goldfarb-Shanno (L-BFGS) algorithm. This is a limited computational memory quasi-Newton method widely used for deterministic unconstrained…

Machine Learning · Computer Science 2021-02-11 Lucas N. Egidio , Anders Hansson , Bo Wahlberg

Deep neural networks (DNNs) have achieved remarkable success in computer vision; however, training DNNs for satisfactory performance remains challenging and suffers from sensitivity to empirical selections of an optimization algorithm for…

Computer Vision and Pattern Recognition · Computer Science 2020-12-22 Haichao Zhang , Kuangrong Hao , Lei Gao , Bing Wei , Xuesong Tang

In stochastic optimization, using large batch sizes during training can leverage parallel resources to produce faster wall-clock training times per training epoch. However, for both training loss and testing error, recent results analyzing…

Machine Learning · Computer Science 2021-04-21 Linjian Ma , Gabe Montague , Jiayu Ye , Zhewei Yao , Amir Gholami , Kurt Keutzer , Michael W. Mahoney

Deep neural networks (DNNs) have demonstrated dominating performance in many fields; since AlexNet, networks used in practice are going wider and deeper. On the theoretical side, a long line of works has been focusing on training neural…

Machine Learning · Computer Science 2019-06-18 Zeyuan Allen-Zhu , Yuanzhi Li , Zhao Song

Training large-scale deep neural networks (DNNs) is resource-intensive, making model compression a practical necessity. The widely accepted ''learning as compression'' hypothesis posits that training induces structure in network weights,…

Machine Learning · Computer Science 2026-05-18 Pedram Bakhtiarifard , Sophia N. Wilson , Mahmoud Afifi , Jonathan Wenshøj , Raghavendra Selvan

We investigate the potential of applying (D)NN ((deep) neural networks) for approximating nonlinear mappings arising in the finite element discretization of nonlinear PDEs (partial differential equations). As an application, we apply the…

Numerical Analysis · Mathematics 2019-11-14 Tuyen Tran , Aidan Hamilton , Maricela Best McKay , Benjamin Quiring , Panayot S. Vassilevski

The damped Gauss-Newton (dGN) algorithm for CANDECOMP/PARAFAC (CP) decomposition can handle the challenges of collinearity of factors and different magnitudes of factors; nevertheless, for factorization of an $N$-D tensor of size $I_1\times…

Numerical Analysis · Computer Science 2015-03-20 Anh Huy Phan , Petr Tichavský , Andrzej Cichocki

We analyze the DQN reinforcement learning algorithm as a stochastic approximation scheme using the o.d.e. (for 'ordinary differential equation') approach and point out certain theoretical issues. We then propose a modified scheme called…

Machine Learning · Computer Science 2021-05-05 K. E. Avrachenkov , V. S. Borkar , H. P. Dolhare , K. Patil

We introduce a novel method to compute a rank $m$ approximation of the inverse of the Hessian matrix in the distributed regime. By leveraging the differences in gradients and parameters of multiple Workers, we are able to efficiently…

Machine Learning · Computer Science 2017-09-18 Sébastien M. R. Arnold , Chunming Wang

In federated learning (FL), the significant communication overhead due to the slow convergence speed of training the global model poses a great challenge. Specifically, a large number of communication rounds are required to achieve the…

Machine Learning · Computer Science 2024-03-19 Mrinmay Sen , A. K. Qin , Krishna Mohan C

Bayesian optimization is a highly efficient approach to optimizing objective functions which are expensive to query. These objectives are typically represented by Gaussian process (GP) surrogate models which are easy to optimize and support…

Machine Learning · Computer Science 2024-05-09 Yucen Lily Li , Tim G. J. Rudner , Andrew Gordon Wilson

We present a quasi-Newton method for unconstrained stochastic optimization. Most existing literature on this topic assumes a setting of stochastic optimization in which a finite sum of component functions is a reasonable approximation of an…

Optimization and Control · Mathematics 2024-09-04 Matt Menickelly , Stefan M. Wild , Miaolan Xie