paper-with-me

홈 › Papers

PCA in Data-Dependent Noise (Correlated-PCA): Nearly Optimal Finite Sample Guarantees

2017-02-10 · Namrata Vaswani, Praneeth Narayanamurthy

We study Principal Component Analysis (PCA) in a setting where a part of the corrupting noise is data-dependent and, as a result, the noise and the true data are correlated. Under a bounded-ness assumption on the true data and the noise, and a simple assumption on data-noise correlation, we obtain a nearly optimal sample complexity bound for the most commonly used PCA solution, singular value decomposition (SVD). This bound is a significant improvement over the bound obtained by Vaswani and Guo in recent work (NIPS 2016) where this "correlated-PCA" problem was first studied; and it holds under a significantly weaker data-noise correlation assumption than the one used for this earlier result.

📄 PDF Abstract BibTeX arXiv:1702.03070

Code (0)

등록된 구현이 없습니다.

Methods 이 논문이 사용한 방법론

PCA Principle Components Analysis (PCA) is an unsupervised method primary used for dimensionality reduction within machine learning. PCA is calculated via a singular value…

Similar Papers 제목 키워드 기반

Gradient Descent with Linearly Correlated Noise: Theory and Applications to Differential Privacy

2023-02-02 · NeurIPS 2023 11 · Anastasia Koloskova, Ryan McKenna, Zachary Charles, Keith Rush 외

We study gradient descent under linearly correlated noise. Our work is motivated by recent practical methods for optimization with differential privacy (DP), such as DP-FTRL, which achieve strong performance in settings …

Federated Learning

Privacy Amplification for Matrix Mechanisms

2023-10-24 · Christopher A. Choquette-Choo, Arun Ganesh, Thomas Steinke, Abhradeep Thakurta

Privacy amplification exploits randomness in data selection to provide tighter differential privacy (DP) guarantees. This analysis is key to DP-SGD's success in machine learning, but, is not readily applicable to the new…

Finite Sample Guarantees for PCA in Non-Isotropic and Data-Dependent Noise

2017-09-19 · Namrata Vaswani, Praneeth Narayanamurthy

This work obtains novel finite sample guarantees for Principal Component Analysis (PCA). These hold even when the corrupting noise is non-isotropic, and a part (or all of it) is data-dependent. Because of the latter, in …

Unsupervised Denoising for Signal-Dependent and Row-Correlated Imaging Noise

2023-10-11 · Benjamin Salmon, Alexander Krull

Accurate analysis of microscopy images is hindered by the presence of noise. This noise is usually signal-dependent and often additionally correlated along rows or columns of pixels. Current self- and unsupervised denois…

DecoderDenoisingImage Denoising

Nearly Instance-Optimal Parameter Recovery from Many Trajectories via Hellinger Localization

2025-10-07 · Eliot Shekhtman, Yichen Zhou, Ingvar Ziemann, Nikolai Matni 외 arxiv

Learning from temporally-correlated data is a core facet of modern machine learning. Yet our understanding of sequential learning remains incomplete, particularly in the multi-trajectory setting where data consists of ma…