English
Related papers

Related papers: Efficient Second Order Online Learning by Sketchin…

200 papers

Stochastic variance reduction has proven effective at accelerating first-order algorithms for solving convex finite-sum optimization tasks such as empirical risk minimization. Incorporating second-order information has proven helpful in…

Optimization and Control · Mathematics 2025-04-30 Michał Dereziński

We introduce SONO, a novel method leveraging Second-Order Neural Ordinary Differential Equations (Second-Order NODEs) to enhance cross-modal few-shot learning. By employing a simple yet effective architecture consisting of a Second-Order…

Computer Vision and Pattern Recognition · Computer Science 2024-12-23 Yi Zhang , Chun-Wun Cheng , Junyi He , Zhihai He , Carola-Bibiane Schönlieb , Yuyan Chen , Angelica I Aviles-Rivero

The regret bound of dynamic online learning algorithms is often expressed in terms of the variation in the function sequence ($V_T$) and/or the path-length of the minimizer sequence after $T$ rounds. For strongly convex and smooth…

Machine Learning · Computer Science 2020-08-17 Ting-Jui Chang , Shahin Shahrampour

We consider sketching algorithms which first quickly compress data by multiplication with a random sketch matrix, and then apply the sketch to quickly solve an optimization problem, e.g., low rank approximation. In the learning-based…

Machine Learning · Computer Science 2021-06-08 Simin Liu , Tianrui Liu , Ali Vakilian , Yulin Wan , David P. Woodruff

The amount of data in our society has been exploding in the era of big data today. In this paper, we address several open challenges of big data stream classification, including high volume, high velocity, high dimensionality, high…

Machine Learning · Computer Science 2015-07-28 Dayong Wang , Pengcheng Wu , Peilin Zhao , Steven C. H. Hoi

We propose a randomized first order optimization method--SEGA (SkEtched GrAdient method)-- which progressively throughout its iterations builds a variance-reduced estimate of the gradient from random linear measurements (sketches) of the…

Optimization and Control · Mathematics 2018-10-19 Filip Hanzely , Konstantin Mishchenko , Peter Richtarik

Sketching, a dimensionality reduction technique, has received much attention in the statistics community. In this paper, we study sketching in the context of Newton's method for solving finite-sum optimization problems in which the number…

Optimization and Control · Mathematics 2019-06-03 Albert S. Berahas , Raghu Bollapragada , Jorge Nocedal

Sketching algorithms have recently proven to be a powerful approach both for designing low-space streaming algorithms as well as fast polynomial time approximation schemes (PTAS). In this work, we develop new techniques to extend the…

Data Structures and Algorithms · Computer Science 2023-10-31 Gregory Dexter , Petros Drineas , David P. Woodruff , Taisuke Yasuda

Optimization plays a key role in machine learning. Recently, stochastic second-order methods have attracted much attention due to their low computational cost in each iteration. However, these algorithms might perform poorly especially if…

Machine Learning · Computer Science 2017-10-25 Haishan Ye , Zhihua Zhang

We consider distributed optimization methods for problems where forming the Hessian is computationally challenging and communication is a significant bottleneck. We leverage randomized sketches for reducing the problem dimensions as well as…

Optimization and Control · Mathematics 2022-03-21 Burak Bartan , Mert Pilanci

Recent advances in large language models (LLMs) have enabled strong reasoning capabilities through Chain-of-Thought (CoT) prompting, which elicits step-by-step problem solving, but often at the cost of excessive verbosity in intermediate…

Computation and Language · Computer Science 2025-10-27 Simon A. Aytes , Jinheon Baek , Sung Ju Hwang

We study a stochastic convex bandit problem where the subgaussian noise parameter is assumed to decrease linearly as the learner selects actions closer and closer to the minimizer of the convex loss function. Accordingly, we propose a…

Optimization and Control · Mathematics 2025-01-22 Jingxin Zhan , Yuchen Xin , Kaicheng Jin , Zhihua Zhang

Bandit convex optimization (BCO) is a general framework for online decision making under uncertainty. While tight regret bounds for general convex losses have been established, existing algorithms achieving these bounds have prohibitive…

Machine Learning · Computer Science 2024-10-04 Arun Suggala , Y. Jennifer Sun , Praneeth Netrapalli , Elad Hazan

A methodology for using random sketching in the context of model order reduction for high-dimensional parameter-dependent systems of equations was introduced in [Balabanov and Nouy 2019, Part I]. Following this framework, we here construct…

Numerical Analysis · Mathematics 2022-03-25 Oleg Balabanov , Anthony Nouy

Deep neural networks are usually trained with stochastic gradient descent (SGD), which minimizes objective function using very rough approximations of gradient, only averaging to the real gradient. Standard approaches like momentum or ADAM…

Machine Learning · Computer Science 2023-03-14 Jarek Duda

We investigate online nonlinear regression with continually running recurrent neural network networks (RNNs), i.e., RNN-based online learning. For RNN-based online learning, we introduce an efficient first-order training algorithm that…

Machine Learning · Computer Science 2021-06-01 N. Mert Vural , Selim F. Yilmaz , Fatih Ilhan , Suleyman S. Kozat

Zeroth-order methods have become important tools for solving problems where we have access only to function evaluations. However, the zeroth-order methods only using gradient approximations are $n$ times slower than classical first-order…

Optimization and Control · Mathematics 2022-02-10 Erik Berglund , Sarit Khirirat , Xiaoyu Wang

Sketching is a probabilistic data compression technique that has been largely developed in the computer science community. Numerical operations on big datasets can be intolerably slow; sketching algorithms address this issue by generating a…

Methodology · Statistics 2019-04-04 Daniel Ahfock , William J. Astle , Sylvia Richardson

We study the problem of minimizing a sum of convex objective functions where the components of the objective are available at different nodes of a network and nodes are allowed to only communicate with their neighbors. The use of…

Optimization and Control · Mathematics 2015-04-24 Aryan Mokhtari , Qing Ling , Alejandro Ribeiro

High-dimensional representations, such as radial basis function networks or tile coding, are common choices for policy evaluation in reinforcement learning. Learning with such high-dimensional representations, however, can be expensive,…

Machine Learning · Computer Science 2017-08-07 Yangchen Pan , Erfan Sadeqi Azer , Martha White