English
Related papers

Related papers: Sketchy: Memory-efficient Adaptive Regularization …

200 papers

Training Neural Ordinary Differential Equations (ODEs) is often computationally expensive. Indeed, computing the forward pass of such models involves solving an ODE which can become arbitrarily complex during training. Recent works have…

Machine Learning · Computer Science 2020-11-03 Arnab Ghosh , Harkirat Singh Behl , Emilien Dupont , Philip H. S. Torr , Vinay Namboodiri

We study three families of online convex optimization algorithms: follow-the-proximally-regularized-leader (FTRL-Proximal), regularized dual averaging (RDA), and composite-objective mirror descent. We first prove equivalence theorems that…

Machine Learning · Computer Science 2011-09-21 H. Brendan McMahan

Learning-based low rank approximation algorithms can significantly improve the performance of randomized low rank approximation with sketch matrix. With the learned value and fixed non-zero positions for sketch matrices from learning-based…

Machine Learning · Computer Science 2022-12-19 Tiejin Chen , Yicheng Tao

Randomized algorithms are important for solving large-scale optimization problems. In this paper, we propose a fast sketching algorithm for least square problems regularized by convex or nonconvex regularization functions, Sketching for…

Optimization and Control · Mathematics 2023-11-06 Yingzhen Yang , Ping Li

We study the problem of Online Convex Optimization (OCO) with memory, which allows loss functions to depend on past decisions and thus captures temporal effects of learning problems. In this paper, we introduce dynamic policy regret as the…

Machine Learning · Computer Science 2023-08-16 Peng Zhao , Yu-Hu Yan , Yu-Xiang Wang , Zhi-Hua Zhou

Implicit regularization is an important way to interpret neural networks. Recent theory starts to explain implicit regularization with the model of deep matrix factorization (DMF) and analyze the trajectory of discrete gradient dynamics in…

Machine Learning · Computer Science 2023-08-14 Jian Cao , Chen Qian , Yihui Huang , Dicheng Chen , Yuncheng Gao , Jiyang Dong , Di Guo , Xiaobo Qu

Approximate matrix multiplication with limited space has received ever-increasing attention due to the emergence of large-scale applications. Recently, based on a popular matrix sketching algorithm -- frequent directions, previous work has…

Machine Learning · Computer Science 2024-06-25 Yuanyu Wan , Lijun Zhang

Low-rank modeling has a lot of important applications in machine learning, computer vision and social network analysis. While the matrix rank is often approximated by the convex nuclear norm, the use of nonconvex low-rank regularizers has…

Numerical Analysis · Computer Science 2016-05-02 Quanming Yao , James T. Kwok , Wenliang Zhong

We consider the problem of universal dynamic regret minimization under exp-concave and smooth losses. We show that appropriately designed Strongly Adaptive algorithms achieve a dynamic regret of $\tilde O(d^2 n^{1/5} C_n^{2/5} \vee d^2)$,…

Machine Learning · Computer Science 2023-02-28 Dheeraj Baby , Yu-Xiang Wang

We revisit the Follow the Regularized Leader (FTRL) framework for Online Convex Optimization (OCO) over compact sets, focusing on achieving dynamic regret guarantees. Prior work has highlighted the framework's limitations in dynamic…

Machine Learning · Computer Science 2026-03-19 Naram Mhaisen , George Iosifidis

Multi-epoch, small-batch, Stochastic Gradient Descent (SGD) has been the method of choice for learning with large over-parameterized models. A popular theory for explaining why SGD works well in practice is that the algorithm has an…

Machine Learning · Computer Science 2021-07-13 Satyen Kale , Ayush Sekhari , Karthik Sridharan

Second-order optimization methods, which leverage curvature information, offer faster and more stable convergence than first-order methods such as stochastic gradient descent (SGD) and Adam. However, their practical adoption is hindered by…

Emerging Technologies · Computer Science 2025-12-08 Saitao Zhang , Yubiao Luo , Shiqing Wang , Pushen Zuo , Yongxiang Li , Lunshuai Pan , Zheng Miao , Zhong Sun

Attention mechanisms have revolutionized sequence learning but suffer from quadratic computational complexity. This paper introduces \model, a novel recurrent neural network (RNN) mechanism that leverages the inherent low-rank structure of…

Machine Learning · Computer Science 2026-01-01 Mahdi Karami , Razvan Pascanu , Vahab Mirrokni

Ensuring the robustness of deep neural networks against adversarial attacks remains a fundamental challenge in computer vision. While adversarial training (AT) has emerged as a promising defense strategy, our analysis reveals a critical…

Computer Vision and Pattern Recognition · Computer Science 2025-01-14 Kejia Zhang , Juanjuan Weng , Yuanzheng Cai , Zhiming Luo , Shaozi Li

Motivated by the study of matrix elimination orderings in combinatorial scientific computing, we utilize graph sketching and local sampling to give a data structure that provides access to approximate fill degrees of a matrix undergoing…

Data Structures and Algorithms · Computer Science 2023-04-11 Matthew Fahrbach , Gary L. Miller , Richard Peng , Saurabh Sawlani , Junxing Wang , Shen Chen Xu

Low-rank optimization has emerged as a promising direction in training large language models (LLMs) to improve running time and reduce the memory usage of adaptive optimizers by constraining learning to a lower-dimensional space. Prior work…

Machine Learning · Computer Science 2025-10-09 Ionut-Vlad Modoranu , Mher Safaryan , Erik Schultheis , Max Ryabinin , Artem Chumachenko , Dan Alistarh

The continuous surge in data volume and velocity is often dealt with using data orchestration and distributed processing approaches, abstracting away the machine learning challenges that exist at the algorithmic level. With growing interest…

Machine Learning · Computer Science 2025-03-04 Behraj Khan , Behroz Mirza , Nouman Durrani , Tahir Syed

Matrix sketching, aimed at approximating a matrix $\boldsymbol{A} \in \mathbb{R}^{N\times d}$ consisting of vector streams of length $N$ with a smaller sketching matrix $\boldsymbol{B} \in \mathbb{R}^{\ell\times d}, \ell \ll N$, has…

Databases · Computer Science 2024-11-06 Hanyan Yin , Dongxie Wen , Jiajun Li , Zhewei Wei , Xiao Zhang , Zengfeng Huang , Feifei Li

We focus on the task of approximating the optimal value function in deep reinforcement learning. This iterative process is comprised of solving a sequence of optimization problems where the loss function changes per iteration. The common…

Machine Learning · Computer Science 2023-11-16 Kavosh Asadi , Rasool Fakoor , Shoham Sabach

We introduce a "learning-based" algorithm for the low-rank decomposition problem: given an $n \times d$ matrix $A$, and a parameter $k$, compute a rank-$k$ matrix $A'$ that minimizes the approximation loss $\|A-A'\|_F$. The algorithm uses a…

Machine Learning · Computer Science 2019-10-31 Piotr Indyk , Ali Vakilian , Yang Yuan
‹ Prev 1 3 4 5 6 7 10 Next ›