paper-with-me

Papers

Stochastic Approximation for Canonical Correlation Analysis

2017-02-22 · NeurIPS 2017 12 · Raman Arora, Teodor V. Marinov, Poorya Mianjy, Nathan Srebro

We propose novel first-order stochastic approximation algorithms for canonical correlation analysis (CCA). Algorithms presented are instances of inexact matrix stochastic gradient (MSG) and inexact matrix exponentiated gradient (MEG), and achieve $\epsilon$-suboptimality in the population objective in $\operatorname{poly}(\frac{1}{\epsilon})$ iterations. We also consider practical variants of the proposed algorithms and compare them with other methods for CCA both theoretically and empirically.

📄 PDF Abstract BibTeX arXiv:1702.06818

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

ORCCA: Optimal Randomized Canonical Correlation Analysis

2019-10-11 · Yinsong Wang, Shahin Shahrampour

Random features approach has been widely used for kernel approximation in large-scale machine learning. A number of recent studies have explored data-dependent sampling of features, modifying the stochastic oracle from w…

BIG-bench Machine Learningscoring rule

Canonical correlation analysis of stochastic trends via functional approximation

2024-11-29 · Massimo Franchi, Iliyan Georgiev, Paolo Paruolo

This paper proposes a novel canonical correlation analysis for semiparametric inference in $I(1)/I(0)$ systems via functional approximation. The approach can be applied coherently to panels of $p$ variables with a generi…

Gen-Oja: A Two-time-scale approach for Streaming CCA

2018-11-20 · Kush Bhatia, Aldo Pacchiano, Nicolas Flammarion, Peter L. Bartlett 외

In this paper, we study the problems of principal Generalized Eigenvector computation and Canonical Correlation Analysis in the stochastic setting. We propose a simple and efficient algorithm, Gen-Oja, for these problems…

Vocal Bursts Valence Prediction

Gen-Oja: Simple & Efficient Algorithm for Streaming Generalized Eigenvector Computation

2018-12-01 · NeurIPS 2018 12 · Kush Bhatia, Aldo Pacchiano, Nicolas Flammarion, Peter L. Bartlett 외

In this paper, we study the problems of principle Generalized Eigenvector computation and Canonical Correlation Analysis in the stochastic setting. We propose a simple and efficient algorithm for these problems. We prove…

Nonconvex Stochastic Scaled-Gradient Descent and Generalized Eigenvector Problems

2021-12-29 · Chris Junchi Li, Michael I. Jordan

Motivated by the problem of online canonical correlation analysis, we propose the \emph{Stochastic Scaled-Gradient Descent} (SSGD) algorithm for minimizing the expectation of a stochastic function over a generic Riemanni…