English
Related papers

Related papers: Comparing BFGS and OGR for Second-Order Optimizati…

200 papers

Newton's method is the most widespread high-order method, demanding the gradient and the Hessian of the objective function. However, one of the main disadvantages of Newtons method is its lack of global convergence and high iteration cost.…

In this paper, we propose a Dimension-Reduced Second-Order Method (DRSOM) for convex and nonconvex (unconstrained) optimization. Under a trust-region-like framework, our method preserves the convergence of the second-order method while…

Optimization and Control · Mathematics 2023-07-04 Chuwen Zhang , Dongdong Ge , Chang He , Bo Jiang , Yuntian Jiang , Yinyu Ye

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

We propose a modified BFGS algorithm for multiobjective optimization problems with global convergence, even in the absence of convexity assumptions on the objective functions. Furthermore, we establish the superlinear convergence of the…

Optimization and Control · Mathematics 2024-04-12 L. F. Prudente , D. R. Souza

Online and stochastic gradient methods have emerged as potent tools in large scale optimization with both smooth convex and nonsmooth convex problems from the classes $C^{1,1}(\reals^p)$ and $C^{1,0}(\reals^p)$ respectively. However to our…

Numerical Analysis · Mathematics 2014-10-30 Ziqiang Shi , Rujie Liu

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

Second-order methods, which utilize gradients as well as Hessians to optimize a given function, are of major importance in mathematical optimization. In this work, we prove tight bounds on the oracle complexity of such methods for smooth…

Optimization and Control · Mathematics 2017-08-18 Yossi Arjevani , Ohad Shamir , Ron Shiff

We derive methods to compute higher order differentials (Hessians and Hessian-vector products) of the rendering operator. Our approach is based on importance sampling of a convolution that represents the differentials of rendering…

Graphics · Computer Science 2025-08-07 Zican Wang , Michael Fischer , Tobias Ritschel

Memory-efficient optimization methods have recently gained increasing attention for scaling full-parameter training of large language models under the GPU-memory bottleneck. Existing approaches either lack clear convergence guarantees, or…

Machine Learning · Computer Science 2026-03-11 Hui Yang , Tao Ren , Jinyang Jiang , Wan Tian , Yijie Peng

In this paper, we propose a second order optimization method to learn models where both the dimensionality of the parameter space and the number of training samples is high. In our method, we construct on each iteration a Krylov subspace…

Machine Learning · Statistics 2011-11-21 Oriol Vinyals , Daniel Povey

This paper introduces a new stochastic optimization method based on the regularized Fisher information matrix (FIM), named SOFIM, which can efficiently utilize the FIM to approximate the Hessian matrix for finding Newton's gradient update…

Machine Learning · Computer Science 2024-05-02 Mrinmay Sen , A. K. Qin , Gayathri C , Raghu Kishore N , Yen-Wei Chen , Balasubramanian Raman

Differentiable optimization layers enable learning systems to make decisions by solving embedded optimization problems. However, computing gradients via implicit differentiation requires solving a linear system with Hessian terms, which is…

Machine Learning · Computer Science 2025-12-03 Zihao Zhao , Kai-Chia Mo , Shing-Hei Ho , Brandon Amos , Kai Wang

We provide a new adaptive method for online convex optimization, MetaGrad, that is robust to general convex losses but achieves faster rates for a broad class of special functions, including exp-concave and strongly convex functions, but…

Machine Learning · Computer Science 2021-08-31 Tim van Erven , Wouter M. Koolen , Dirk van der Hoeven

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

Trust-region (TR) and adaptive regularization using cubics (ARC) have proven to have some very appealing theoretical properties for non-convex optimization by concurrently computing function value, gradient, and Hessian matrix to obtain the…

Machine Learning · Computer Science 2023-10-19 Liu Liu , Xuanqing Liu , Cho-Jui Hsieh , Dacheng Tao

This paper describes an implementation of the L-BFGS method designed to deal with two adversarial situations. The first occurs in distributed computing environments where some of the computational nodes devoted to the evaluation of the…

Optimization and Control · Mathematics 2019-08-28 Albert S. Berahas , Martin Takáč

Non-asymptotic analysis of quasi-Newton methods have gained traction recently. In particular, several works have established a non-asymptotic superlinear rate of $\mathcal{O}((1/\sqrt{t})^t)$ for the (classic) BFGS method by exploiting the…

Optimization and Control · Mathematics 2022-06-17 Qiujiang Jin , Alec Koppel , Ketan Rajawat , Aryan Mokhtari

Gradient regularization (GR) has been shown to improve the generalizability of trained models. While Natural Gradient Descent has been shown to accelerate optimization in the initial phase of training, little attention has been paid to how…

Machine Learning · Computer Science 2026-03-27 Satya Prakash Dash , Hossein Abdi , Wei Pan , Samuel Kaski , Mingfei Sun

Reliable decision-making with streaming data requires principled uncertainty quantification of online methods. While first-order methods enable efficient iterate updates, their inference procedures still require updating proper (covariance)…

Machine Learning · Statistics 2026-04-28 Haoxuan Wang , Xinchen Du , Sen Na

We devise an L-BFGS method for optimization problems in which the objective is the sum of two functions, where the Hessian of the first function is computationally unavailable while the Hessian of the second function has a computationally…

Optimization and Control · Mathematics 2024-09-10 Florian Mannel , Hari Om Aggrawal