English
Related papers

Related papers: A Stochastic Quasi-Newton Method for Large-Scale O…

200 papers

Many practical optimization problems involve objective function values that are corrupted by unavoidable numerical errors. In smooth nonconvex optimization, quasi-Newton methods combined with line search are widely used due to their…

Optimization and Control · Mathematics 2026-03-12 Hiroki Hamaguchi , Naoki Marumo , Akiko Takeda

This work presents a novel version of recently developed Gauss-Newton method for solving systems of nonlinear equations, based on upper bound of solution residual and quadratic regularization ideas. We obtained for such method global…

Optimization and Control · Mathematics 2021-05-04 Nikita Yudin , Alexander Gasnikov

Non linear regression models are a standard tool for modeling real phenomena, with several applications in machine learning, ecology, econometry... Estimating the parameters of the model has garnered a lot of attention during many years. We…

Statistics Theory · Mathematics 2020-09-17 Peggy Cénac , Antoine Godichon-Baggioni , Bruno Portier

Standard first-order stochastic optimization algorithms base their updates solely on the average mini-batch gradient, and it has been shown that tracking additional quantities such as the curvature can help de-sensitize common…

Machine Learning · Computer Science 2020-11-11 Ricky T. Q. Chen , Dami Choi , Lukas Balles , David Duvenaud , Philipp Hennig

We present a novel statistical inference framework for convex empirical risk minimization, using approximate stochastic Newton steps. The proposed algorithm is based on the notion of finite differences and allows the approximation of a…

Machine Learning · Computer Science 2019-02-06 Tianyang Li , Anastasios Kyrillidis , Liu Liu , Constantine Caramanis

Recently a majorization method for optimizing partition functions of log-linear models was proposed alongside a novel quadratic variational upper-bound. In the batch setting, it outperformed state-of-the-art first- and second-order…

Machine Learning · Computer Science 2013-09-24 Anna Choromanska , Tony Jebara

Despite the impressive numerical performance of the quasi-Newton and Anderson/nonlinear acceleration methods, their global convergence rates have remained elusive for over 50 years. This study addresses this long-standing issue by…

Optimization and Control · Mathematics 2023-11-16 Damien Scieur

We extend the well-known BFGS quasi-Newton method and its memory-limited variant LBFGS to the optimization of nonsmooth convex objectives. This is done in a rigorous fashion by generalizing three components of BFGS to subdifferentials: the…

Machine Learning · Statistics 2010-11-30 Jin Yu , S. V. N. Vishwanathan , Simon Guenter , Nicol N. Schraudolph

Recent studies have illustrated that stochastic gradient Markov Chain Monte Carlo techniques have a strong potential in non-convex optimization, where local and global convergence guarantees can be shown under certain conditions. By…

Machine Learning · Statistics 2018-06-08 Umut Şimşekli , Çağatay Yıldız , Thanh Huy Nguyen , Gaël Richard , A. Taylan Cemgil

We consider the problem of minimizing the average of a large number of smooth but possibly non-convex functions. In the context of most machine learning applications, each loss function is non-negative and thus can be expressed as the…

Optimization and Control · Mathematics 2024-07-08 Antonio Orvieto , Lin Xiao

Stochastic gradient updates are widely used for their efficiency and scalability, but their effective step sizes can depend strongly on feature scaling and local model sensitivity. Gauss-Newton methods address such scale effects through…

Machine Learning · Computer Science 2026-05-27 Mikalai Korbit , Mario Zanon

RES, a regularized stochastic version of the Broyden-Fletcher-Goldfarb-Shanno (BFGS) quasi-Newton method is proposed to solve convex optimization problems with stochastic objectives. The use of stochastic gradient descent algorithms is…

Machine Learning · Computer Science 2015-06-18 Aryan Mokhtari , Alejandro Ribeiro

Stochastic gradient algorithms are the main focus of large-scale optimization problems and led to important successes in the recent advancement of the deep learning algorithms. The convergence of SGD depends on the careful choice of…

Machine Learning · Computer Science 2017-03-03 Caglar Gulcehre , Jose Sotelo , Marcin Moczulski , Yoshua Bengio

We introduce some new proximal quasi-Newton methods for unconstrained multiobjective optimization problems (in short, UMOP), where each objective function is the sum of a twice continuously differentiable strongly convex function and a…

Optimization and Control · Mathematics 2022-04-08 Jian-Wen Peng , Jie Ren

Many structured data-fitting applications require the solution of an optimization problem involving a sum over a potentially large number of measurements. Incremental gradient algorithms offer inexpensive iterations by sampling a subset of…

Numerical Analysis · Computer Science 2018-08-23 Michael P. Friedlander , Mark Schmidt

We introduce the primal-dual quasi-Newton (PD-QN) method as an approximated second order method for solving decentralized optimization problems. The PD-QN method performs quasi-Newton updates on both the primal and dual variables of the…

Optimization and Control · Mathematics 2020-01-08 Mark Eisen , Aryan Mokhtari , Alejandro Ribeiro

We develop methods for parameter estimation in settings with large-scale data sets, where traditional methods are no longer tenable. Our methods rely on stochastic approximations, which are computationally efficient as they maintain one…

Computation · Statistics 2015-09-23 Dustin Tran , Panos Toulis , Edoardo M. Airoldi

Second-order methods for neural network optimization have several advantages over methods based on first-order gradient descent, including better scaling to large mini-batch sizes and fewer updates needed for convergence. But they are…

Machine Learning · Computer Science 2017-12-21 Huishuai Zhang , Caiming Xiong , James Bradbury , Richard Socher

We propose an L-BFGS optimization algorithm on Riemannian manifolds using minibatched stochastic variance reduction techniques for fast convergence with constant step sizes, without resorting to linesearch methods designed to satisfy Wolfe…

Optimization and Control · Mathematics 2017-05-23 Anirban Roychowdhury

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.…

‹ Prev 1 4 5 6 7 8 10 Next ›