English
Related papers

Related papers: Sketchy: Memory-efficient Adaptive Regularization …

200 papers

The frequent directions (FD) technique is a deterministic approach for online sketching that has many applications in machine learning. The conventional FD is a heuristic procedure that often outputs rank deficient matrices. To overcome the…

Machine Learning · Computer Science 2019-02-26 Luo Luo , Cheng Chen , Zhihua Zhang , Wu-Jun Li , Tong Zhang

We describe a new algorithm called Frequent Directions for deterministic matrix sketching in the row-updates model. The algorithm is presented an arbitrary input matrix $A \in R^{n \times d}$ one row at a time. It performed $O(d \times…

Data Structures and Algorithms · Computer Science 2015-04-22 Mina Ghashami , Edo Liberty , Jeff M. Phillips , David P. Woodruff

Preventing catastrophic forgetting while continually learning new tasks is an essential problem in lifelong learning. Structural regularization (SR) refers to a family of algorithms that mitigate catastrophic forgetting by penalizing the…

Machine Learning · Computer Science 2021-04-20 Haoran Li , Aditya Krishnan , Jingfeng Wu , Soheil Kolouri , Praveen K. Pilly , Vladimir Braverman

Many popular first-order optimization methods (e.g., Momentum, AdaGrad, Adam) accelerate the convergence rate of deep learning models. However, these algorithms require auxiliary parameters, which cost additional memory proportional to the…

Machine Learning · Computer Science 2019-02-27 Ryan Spring , Anastasios Kyrillidis , Vijai Mohan , Anshumali Shrivastava

Neural network training relies on gradient computation through backpropagation, yet memory requirements for storing layer activations present significant scalability challenges. We present the first adaptation of control-theoretic matrix…

Machine Learning · Computer Science 2025-10-02 Harbir Antil , Deepanshu Verma

Kernel online convex optimization (KOCO) is a framework combining the expressiveness of non-parametric kernel models with the regret guarantees of online learning. First-order KOCO methods such as functional gradient descent require only…

Machine Learning · Statistics 2017-06-16 Daniele Calandriello , Alessandro Lazaric , Michal Valko

We consider processing an n x d matrix A in a stream with row-wise updates according to a recent algorithm called Frequent Directions (Liberty, KDD 2013). This algorithm maintains an l x d matrix Q deterministically, processing each row in…

Data Structures and Algorithms · Computer Science 2013-08-23 Mina Ghashami , Jeff M. Phillips

Despite its impressive theory \& practical performance, Frequent Directions (\acrshort{fd}) has not been widely adopted for large-scale regression tasks. Prior work has shown randomized sketches (i) perform worse in estimating the…

Machine Learning · Computer Science 2020-11-10 Charlie Dickens

Sketching is a dimensionality reduction technique where one compresses a matrix by linear combinations that are chosen at random. A line of work has shown how to sketch the Hessian to speed up each iteration in a second order method, but…

Machine Learning · Computer Science 2021-10-07 Yi Li , Honghao Lin , David P. Woodruff

We propose a new randomized optimization method for high-dimensional problems which can be seen as a generalization of coordinate descent to random subspaces. We show that an adaptive sampling strategy for the random subspace significantly…

Optimization and Control · Mathematics 2019-12-19 Jonathan Lacotte , Mert Pilanci , Marco Pavone

First-order optimizers are reliable but slow in sharp, anisotropic regions. We study a curvature-adaptive method that periodically sketches a low-rank Hessian subspace via Hessian--vector products and preconditions gradients only in that…

Machine Learning · Computer Science 2025-11-18 Wenzhang Du

We present a novel adaptive optimization algorithm for large-scale machine learning problems. Equipped with a low-cost estimate of local curvature and Lipschitz smoothness, our method dynamically adapts the search direction and step-size.…

Machine Learning · Computer Science 2021-09-14 Majid Jahani , Sergey Rusakov , Zheng Shi , Peter Richtárik , Michael W. Mahoney , Martin Takáč

Second order stochastic optimizers allow parameter update step size and direction to adapt to loss curvature, but have traditionally required too much memory and compute for deep learning. Recently, Shampoo [Gupta et al., 2018] introduced a…

Machine Learning · Statistics 2023-06-01 Jonathan Mei , Alexander Moreno , Luke Walters

This paper describes Sparse Frequent Directions, a variant of Frequent Directions for sketching sparse matrices. It resembles the original algorithm in many ways: both receive the rows of an input matrix $A^{n \times d}$ one by one in the…

Data Structures and Algorithms · Computer Science 2016-02-18 Mina Ghashami , Edo Liberty , Jeff M. Phillips

This paper studies a new design of the optimization algorithm for training deep learning models with a fixed architecture of the classification network in a continual learning framework. The training data is non-stationary and the…

Machine Learning · Computer Science 2022-07-05 Yunfei Teng , Anna Choromanska , Murray Campbell , Songtao Lu , Parikshit Ram , Lior Horesh

We propose a new framework for analyzing zeroth-order optimization (ZOO) from the perspective of \emph{oblivious randomized sketching}.In this framework, commonly used gradient estimators in ZOO-such as finite difference (FD) and random…

Optimization and Control · Mathematics 2025-10-14 Haishan Ye , Xiangyu Chang , Xi Chen

Sketching is one of the most fundamental tools in large-scale machine learning. It enables runtime and memory saving via randomly compressing the original large problem into lower dimensions. In this paper, we propose a novel sketching…

Machine Learning · Computer Science 2023-06-08 Zhao Song , Yitan Wang , Zheng Yu , Lichen Zhang

In online convex optimization (OCO), a decision-maker is confronted with an unknown environment and seeks to play an optimal sequence of decisions on a short time-scale using only past information. Recent advances in second-order OCO…

Optimization and Control · Mathematics 2026-05-28 Jean-Luc Lupien , Yuen-Man Pun , Youssef Diouane , Iman Shames , Antoine Lesage-Landry

We consider sketching algorithms which first 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 and regression. In the learning-based…

Machine Learning · Computer Science 2024-04-12 Yi Li , Honghao Lin , Simin Liu , Ali Vakilian , David P. Woodruff

Stochastic gradient descent (SGD) now acts as a fundamental part of optimization in current machine learning. Meanwhile, deep learning architectures have shown outstanding performance in a wide range of fields, such as natural language…

Machine Learning · Computer Science 2026-01-27 Zhao Song , Song Yue
‹ Prev 1 2 3 10 Next ›