中文
相关论文

相关论文: ISAAC Newton: Input-based Approximate Curvature fo…

200 篇论文

Second-order optimization methods have the ability to accelerate convergence by modifying the gradient through the curvature matrix. There have been many attempts to use second-order optimization methods for training deep neural networks.…

机器学习 · 计算机科学 2020-11-24 Kai-Xin Gao , Xiao-Lei Liu , Zheng-Hai Huang , Min Wang , Zidong Wang , Dachuan Xu , Fan Yu

In this paper, we investigate a general class of stochastic gradient descent (SGD) algorithms, called Conditioned SGD, based on a preconditioning of the gradient direction. Using a discrete-time approach with martingale tools, we establish…

统计理论 · 数学 2023-10-17 Rémi Leluc , François Portier

We propose an optimization proxy in terms of iterative implicit gradient methods for solving constrained optimization problems with nonconvex loss functions. This framework can be applied to a broad range of machine learning settings,…

最优化与控制 · 数学 2025-10-14 Harshal D. Kaushik , Ming Jin

We propose an iterative algorithm for low-rank matrix completion that can be interpreted as both an iteratively reweighted least squares (IRLS) algorithm and a saddle-escaping smoothing Newton method applied to a non-convex rank surrogate…

最优化与控制 · 数学 2020-09-08 Christian Kümmerle , Claudio M. Verdun

In this work, we present a globalized stochastic semismooth Newton method for solving stochastic optimization problems involving smooth nonconvex and nonsmooth convex terms in the objective function. We assume that only noisy gradient and…

最优化与控制 · 数学 2018-03-12 Andre Milzarek , Xiantao Xiao , Shicong Cen , Zaiwen Wen , Michael Ulbrich

We propose two novel conditional gradient-based methods for solving structured stochastic convex optimization problems with a large number of linear constraints. Instances of this template naturally arise from SDP-relaxations of…

机器学习 · 计算机科学 2020-07-09 Maria-Luiza Vladarean , Ahmet Alacaoglu , Ya-Ping Hsieh , Volkan Cevher

We propose a new method for parameter learning in Bayesian networks with qualitative influences. This method extends our previous work from networks of binary variables to networks of discrete variables with ordered values. The specified…

人工智能 · 计算机科学 2012-06-26 Ad Feelders

This paper introduces an iterative algorithm for training nonparametric additive models that enjoys favorable memory storage and computational requirements. The algorithm can be viewed as the functional counterpart of stochastic gradient…

机器学习 · 统计学 2026-01-01 Xin Chen , Jason M. Klusowski

In this paper, we propose a new first-order gradient-based algorithm to train deep neural networks. We first introduce the sign operation of stochastic gradients (as in sign-based methods, e.g., SIGN-SGD) into ADAM, which is called as…

计算机视觉与模式识别 · 计算机科学 2019-07-23 Dong Wang , Yicheng Liu , Wenwo Tang , Fanhua Shang , Hongying Liu , Qigong Sun , Licheng Jiao

We study stochastic inexact Newton methods and consider their application in nonconvex settings. Building on the work of [R. Bollapragada, R. H. Byrd, and J. Nocedal, IMA Journal of Numerical Analysis, 39 (2018), pp. 545--578] we derive…

最优化与控制 · 数学 2019-08-02 Thomas O'Leary-Roseberry , Nick Alger , Omar Ghattas

We suggest simple modifications of the conditional gradient method for smooth optimization problems, which maintain the basic convergence properties, but reduce the implementation cost of each iteration essentially. Namely, we propose the…

最优化与控制 · 数学 2018-01-17 Igor Konnov

High sensitivity of neural architecture search (NAS) methods against their input such as step-size (i.e., learning rate) and search space prevents practitioners from applying them out-of-the-box to their own problems, albeit its purpose is…

机器学习 · 计算机科学 2019-05-22 Youhei Akimoto , Shinichi Shirakawa , Nozomu Yoshinari , Kento Uchida , Shota Saito , Kouhei Nishida

Predictive coding (PC) is a general theory of cortical function. The local, gradient-based learning rules found in one kind of PC model have recently been shown to closely approximate backpropagation. This finding suggests that this…

神经与进化计算 · 计算机科学 2021-12-09 Nick Alonso , Emre Neftci

In training neural networks, it is common practice to use partial gradients computed over batches, mostly very small subsets of the training set. This approach is motivated by the argument that such a partial gradient is close to the true…

机器学习 · 计算机科学 2024-11-25 Jan Spörer , Bernhard Bermeitinger , Tomas Hrycej , Niklas Limacher , Siegfried Handschuh

We develop a principled approach to obtain exact computer-aided worst-case guarantees on the performance of second-order optimization methods on classes of univariate functions. We first present a generic technique to derive interpolation…

最优化与控制 · 数学 2025-07-01 Anne Rubbens , Nizar Bousselmi , Julien M. Hendrickx , François Glineur

Superlinear convergence has been an elusive goal for black-box nonsmooth optimization. Even in the convex case, the subgradient method is very slow, and while some cutting plane algorithms, including traditional bundle methods, are popular…

最优化与控制 · 数学 2019-07-30 Adrian Lewis , Calvin Wylie

Accelerating the convergence of second-order optimization, particularly Newton-type methods, remains a pivotal challenge in algorithmic research. In this paper, we extend previous work on the \textbf{Quadratic Gradient (QG)} and rigorously…

最优化与控制 · 数学 2026-04-01 John Chiang

Non-convex optimization problems are challenging to solve; the success and computational expense of a gradient descent algorithm or variant depend heavily on the initialization strategy. Often, either random initialization is used or…

机器学习 · 计算机科学 2020-12-23 Kartik Ahuja , Amit Dhurandhar , Kush R. Varshney

In this paper, we propose new proximal Newton-type methods for convex optimization problems in composite form. The applications include model predictive control (MPC) and embedded MPC. Our new methods are computationally attractive since…

最优化与控制 · 数学 2020-07-21 Ilan Adler , Zhiyue Tom Hu , Tianyi Lin

This paper presents an auto-conditioned proximal gradient method for nonconvex optimization. The method determines the stepsize using an estimation of local curvature and does not require any prior knowledge of problem parameters and any…

最优化与控制 · 数学 2025-09-19 Shotaro Yagishita , Masaru Ito