English
Related papers

Related papers: Efficient Second Order Online Learning by Sketchin…

200 papers

Online learning algorithms have been successfully used to design caching policies with sublinear regret in the total number of requests, with no statistical assumption about the request sequence. Most existing algorithms involve…

Machine Learning · Computer Science 2025-03-05 Younes Ben Mazziane , Francescomaria Faticanti , Sara Alouf , Giovanni Neglia

How does the choice of training data influence an AI model? This broad question is of central importance to interpretability, privacy, and basic science. At its technical core is the data deletion problem: after a reasonable amount of…

Machine Learning · Computer Science 2026-04-21 Sam Gunn

Federated learning faces a critical challenge in balancing communication efficiency with rapid convergence, especially for second-order methods. While Newton-type algorithms achieve linear convergence in communication rounds, transmitting…

Machine Learning · Computer Science 2024-10-02 Sunny Gupta , Mohit Jindal , Pankhi Kashyap , Pranav Jeevan , Amit Sethi

In the convex optimization approach to online regret minimization, many methods have been developed to guarantee a $O(\sqrt{T})$ bound on regret for subdifferentiable convex loss functions with bounded subgradients, by using a reduction to…

Machine Learning · Computer Science 2016-09-20 Arthur Flajolet , Patrick Jaillet

The goal of a learner in standard online learning is to maintain an average loss close to the loss of the best-performing single function in some class. In many real-world problems, such as rating or ranking items, there is no single best…

Machine Learning · Computer Science 2013-03-18 Edward Moroshko , Koby Crammer

We study the relation between streaming algorithms and linear sketching algorithms, in the context of binary updates. We show that for inputs in $n$ dimensions, the existence of efficient streaming algorithms which can process $\Omega(n^2)$…

Computational Complexity · Computer Science 2018-09-25 Kaave Hosseini , Shachar Lovett , Grigory Yaroslavtsev

We propose Regularized Overestimated Newton (RON), a Newton-type method with low per-iteration cost and strong global and local convergence guarantees for smooth convex optimization. RON interpolates between gradient descent and globally…

Optimization and Control · Mathematics 2025-10-02 Danny Duan , Hanbaek Lyu

It is often desirable to reduce the dimensionality of a large dataset by projecting it onto a low-dimensional subspace. Matrix sketching has emerged as a powerful technique for performing such dimensionality reduction very efficiently. Even…

Machine Learning · Computer Science 2022-06-15 Michał Dereziński , Feynman Liang , Zhenyu Liao , Michael W. Mahoney

We present a sketch-based CAD modeling system, where users create objects incrementally by sketching the desired shape edits, which our system automatically translates to CAD operations. Our approach is motivated by the close similarities…

Graphics · Computer Science 2020-09-11 Changjian Li , Hao Pan , Adrien Bousseau , Niloy J. Mitra

We study outlier (a.k.a., anomaly) detection for single-pass non-stationary streaming data. In the well-studied offline or batch outlier detection problem, traditional methods such as kernel One-Class SVM (OCSVM) are both computationally…

Machine Learning · Statistics 2025-12-15 Joe Suk , Samory Kpotufe

The second-order cone (SOC) is a class of simple convex cones and optimizing over them can be done more efficiently than with semidefinite programming. It is interesting both in theory and in practice to investigate which convex cones admit…

Optimization and Control · Mathematics 2025-04-29 Victor Magron , Jie Wang

We propose and analyze several inexact regularized Newton-type methods for finding a global saddle point of convex-concave unconstrained min-max optimization problems. Compared to first-order methods, our understanding of second-order…

Optimization and Control · Mathematics 2026-05-27 Tianyi Lin , Panayotis Mertikopoulos , Michael I. Jordan

Parameter reduction has been an important topic in deep learning due to the ever-increasing size of deep neural network models and the need to train and run them on resource limited machines. Despite many efforts in this area, there were no…

Machine Learning · Computer Science 2019-02-26 Yibo Lin , Zhao Song , Lin F. Yang

Dual descent methods are commonly used to solve network flow optimization problems, since their implementation can be distributed over the network. These algorithms, however, often exhibit slow convergence rates. Approximate Newton methods…

Optimization and Control · Mathematics 2015-03-25 Rasul Tutunov , Haitham Bou Ammar , Ali Jadbabaie

Sparse regression has been a popular approach to perform variable selection and enhance the prediction accuracy and interpretability of the resulting statistical model. Existing approaches focus on offline regularized regression, while the…

Machine Learning · Statistics 2023-01-03 Shuoguang Yang , Yuhao Yan , Xiuneng Zhu , Qiang Sun

A standard way to obtain convergence guarantees in stochastic convex optimization is to run an online learning algorithm and then output the average of its iterates: the actual iterates of the online learning algorithm do not come with…

Machine Learning · Statistics 2019-03-05 Ashok Cutkosky

We introduce a new sub-linear space sketch---the Weight-Median Sketch---for learning compressed linear classifiers over data streams while supporting the efficient recovery of large-magnitude weights in the model. This enables…

Machine Learning · Computer Science 2018-04-10 Kai Sheng Tai , Vatsal Sharan , Peter Bailis , Gregory Valiant

Quasi-Newton methods refer to a class of algorithms at the interface between first and second order methods. They aim to progress as substantially as second order methods per iteration, while maintaining the computational complexity of…

Optimization and Control · Mathematics 2024-05-14 Shida Wang , Jalal Fadili , Peter Ochs

We study the problem of smooth imitation learning for online sequence prediction, where the goal is to train a policy that can smoothly imitate demonstrated behavior in a dynamic and continuous environment in response to online, sequential…

Machine Learning · Computer Science 2016-06-06 Hoang M. Le , Andrew Kang , Yisong Yue , Peter Carr

Regularized online learning is widely used in machine learning applications. In online learning, performing exact minimization ($i.e.,$ implicit update) is known to be beneficial to the numerical stability and structure of solution. In this…

Machine Learning · Computer Science 2019-02-08 Chaobing Song , Ji Liu , Han Liu , Yong Jiang , Tong Zhang
‹ Prev 1 8 9 10 Next ›