English
Related papers

Related papers: OverSketched Newton: Fast Convex Optimization for …

200 papers

Low-rank approximation in data streams is a fundamental and significant task in computing science, machine learning and statistics. Multiple streaming algorithms have emerged over years and most of them are inspired by randomized…

Data Structures and Algorithms · Computer Science 2022-09-30 Cuiyu Liu , Chuanfu Xiao , Mingshuo Ding , Chao Yang

This paper presents new projection-free algorithms for Online Convex Optimization (OCO) over a convex domain $\mathcal{K} \subset \mathbb{R}^d$. Classical OCO algorithms (such as Online Gradient Descent) typically need to perform Euclidean…

Optimization and Control · Mathematics 2023-06-21 Khashayar Gatmiry , Zakaria Mhammedi

In this work, we study distributed sketching methods for large scale regression problems. We leverage multiple randomized sketches for reducing the problem dimensions as well as preserving privacy and improving straggler resilience in…

Distributed, Parallel, and Cluster Computing · Computer Science 2020-06-23 Burak Bartan , Mert Pilanci

Kernel methods are learning algorithms that enjoy solid theoretical foundations while suffering from important computational limitations. Sketching, which consists in looking for solutions among a subspace of reduced dimension, is a well…

Machine Learning · Statistics 2023-11-07 Tamim El Ahmad , Pierre Laforgue , Florence d'Alché-Buc

Machine unlearning strives to uphold the data owners' right to be forgotten by enabling models to selectively forget specific data. Recent advances suggest pre-computing and storing statistics extracted from second-order information and…

Machine Learning · Computer Science 2025-02-07 Xinbao Qiao , Meng Zhang , Ming Tang , Ermin Wei

Training of convolutional neural networks is a high dimensional and a non-convex optimization problem. At present, it is inefficient in situations where parametric learning rates can not be confidently set. Some past works have introduced…

Machine Learning · Computer Science 2023-04-06 Ujjwal Thakur , Anuj Sharma

Randomized algorithms for very large matrix problems have received a great deal of attention in recent years. Much of this work was motivated by problems in large-scale data analysis, and this work was performed by individuals from many…

Data Structures and Algorithms · Computer Science 2011-11-16 Michael W. Mahoney

Nowadays, analysing data from different classes or over a temporal grid has attracted a great deal of interest. As a result, various multiple graphical models for learning a collection of graphical models simultaneously have been derived by…

Optimization and Control · Mathematics 2021-04-23 Ning Zhang , Yangjing Zhang , Defeng Sun , Kim-Chuan Toh

Majorization-minimization schemes are a broad class of iterative methods targeting general optimization problems, including nonconvex, nonsmooth and stochastic. These algorithms minimize successively a sequence of upper bounds of the…

Optimization and Control · Mathematics 2024-01-11 Daniela Lupu , Ion Necoara

Recently, Bessa et al. (PODS 2023) showed that sketches based on coordinated weighted sampling theoretically and empirically outperform popular linear sketching methods like Johnson-Lindentrauss projection and CountSketch for the ubiquitous…

Databases · Computer Science 2024-08-23 Majid Daliri , Juliana Freire , Christopher Musco , Aécio Santos , Haoxiang Zhang

We develop a quantum-classical hybrid algorithm for function optimization that is particularly useful in the training of neural networks since it makes use of particular aspects of high-dimensional energy landscapes. Due to a recent…

Quantum Physics · Physics 2017-10-20 Leonard Wossnig , Sebastian Tschiatschek , Stefan Zohren

Nonconvex optimization problems such as the ones in training deep neural networks suffer from a phenomenon called saddle point proliferation. This means that there are a vast number of high error saddle points present in the loss function.…

Numerical Analysis · Computer Science 2016-11-08 Martin Arjovsky

In this paper, we propose objective-function-free (OFF) variants of the proximal Newton method for nonconvex composite optimization problems and the regularized Newton method for unconstrained optimization problems, respectively, using…

Optimization and Control · Mathematics 2026-05-19 Hong Zhu

Quasi-Newton (QN) methods provide an efficient alternative to second-order methods for minimizing smooth unconstrained problems. While QN methods generally compose a Hessian estimate based on one secant interpolation per iteration,…

Optimization and Control · Mathematics 2025-04-11 Mokhwa Lee , Yifan Sun

Large-scale distributed training of neural networks is often limited by network bandwidth, wherein the communication time overwhelms the local computation time. Motivated by the success of sketching methods in sub-linear/streaming…

Machine Learning · Computer Science 2020-01-24 Nikita Ivkin , Daniel Rothchild , Enayat Ullah , Vladimir Braverman , Ion Stoica , Raman Arora

Progress in deep learning is slowed by the days or weeks it takes to train large models. The natural solution of using more hardware is limited by diminishing returns, and leads to inefficient use of additional resources. In this paper, we…

Machine Learning · Computer Science 2017-12-12 Shankar Krishnan , Ying Xiao , Rif A. Saurous

A central challenge to many fields of science and engineering involves minimizing non-convex error functions over continuous, high dimensional spaces. Gradient descent or quasi-Newton methods are almost ubiquitously used to perform such…

Machine Learning · Computer Science 2014-05-29 Razvan Pascanu , Yann N. Dauphin , Surya Ganguli , Yoshua Bengio

Matrix trace estimation is ubiquitous in machine learning applications and has traditionally relied on Hutchinson's method, which requires $O(\log(1/\delta)/\epsilon^2)$ matrix-vector product queries to achieve a $(1 \pm…

Data Structures and Algorithms · Computer Science 2021-11-02 Shuli Jiang , Hai Pham , David P. Woodruff , Qiuyi , Zhang

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

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