中文
相关论文

相关论文: Simple, unified analysis of Johnson-Lindenstrauss …

200 篇论文

The Johnson--Lindenstrauss (JL) lemma is a powerful tool for dimensionality reduction in modern algorithm design. The lemma states that any set of high-dimensional points in a Euclidean space can be flattened to lower dimensions while…

概率论 · 数学 2024-11-08 Kwassi Joseph Dzahini , Stefan M. Wild

The Johnson-Lindenstrauss (JL) lemma is a cornerstone of dimensionality reduction in Euclidean space, but its applicability to non-Euclidean data has remained limited. This paper extends the JL lemma beyond Euclidean geometry to handle…

数据结构与算法 · 计算机科学 2025-10-28 Chengyuan Deng , Jie Gao , Kevin Lu , Feng Luo , Cheng Xin

We provide a simple proof of the Johnson-Lindenstrauss lemma for sub-Gaussian variables. We extend the analysis to identify how sparse projections can be, and what the cost of sparsity is on the target dimension.The Johnson-Lindenstrauss…

统计理论 · 数学 2024-09-25 Aurélien Garivier , Emmanuel Pilliat

In this paper we make a novel use of the Johnson-Lindenstrauss Lemma. The Lemma has an existential form saying that there exists a JL transformation $f$ of the data points into lower dimensional space such that all of them fall into…

数据结构与算法 · 计算机科学 2017-11-10 Mieczysław A. Kłopotek

Embeddings play a pivotal role across various disciplines, offering compact representations of complex data structures. Randomized methods like Johnson-Lindenstrauss (JL) provide state-of-the-art and essentially unimprovable theoretical…

机器学习 · 统计学 2024-12-11 Nikos Tsikouras , Constantine Caramanis , Christos Tzamos

Allen-Zhu, Gelashvili, Micali, and Shavit construct a sparse, sign-consistent Johnson-Lindenstrauss distribution, and prove that this distribution yields an essentially optimal dimension for the correct choice of sparsity. However, their…

数据结构与算法 · 计算机科学 2019-10-01 Meena Jagadeesan

We present a theory for Euclidean dimensionality reduction with subgaussian matrices which unifies several restricted isometry property and Johnson-Lindenstrauss type results obtained earlier for specific data sets. In particular, we…

信息论 · 计算机科学 2014-02-18 Sjoerd Dirksen

Dimensionality reduction-based dictionary learning methods in the literature have often used iterative random projections. The dimensionality of such a random projection matrix is a random number that might not lead to a separable subspace…

计算机视觉与模式识别 · 计算机科学 2026-03-17 G. Madhuri , Atul Negi , Kaluri V. Rangarao

The famous Johnson-Lindenstrauss lemma states that for any set of n vectors, there is a linear transformation into a space of dimension O(log n) that approximately preserves all their lengths. In fact, a Haar random unitary transformation…

量子物理 · 物理学 2018-07-25 Pranab Sen

We consider the problem of efficient randomized dimensionality reduction with norm-preservation guarantees. Specifically we prove data-dependent Johnson-Lindenstrauss-type geometry preservation guarantees for Ho's random subspace method:…

机器学习 · 统计学 2017-05-19 Nick Lim , Robert J. Durrant

Uniform bounds on sketched inner products of vectors or matrices underpin several important computational and statistical results in machine learning and randomized algorithms, including the Johnson-Lindenstrauss (J-L) lemma, the Restricted…

机器学习 · 计算机科学 2025-09-29 Rohan Deb , Qiaobo Li , Mayank Shrivastava , Arindam Banerjee

The Johnson-Lindenstrauss Lemma states that there exist linear maps that project a set of points of a vector space into a space of much lower dimension such that the Euclidean distance between these points is approximately preserved. This…

最优化与控制 · 数学 2023-01-18 Pierre-Louis Poirion , Bruno F. Lourenço , Akiko Takeda

In this paper, we propose a unified algorithmic framework for solving many known variants of \mds. Our algorithm is a simple iterative scheme with guaranteed convergence, and is \emph{modular}; by changing the internals of a single…

机器学习 · 计算机科学 2010-03-31 Arvind Agarwal , Jeff M. Phillips , Suresh Venkatasubramanian

The Johnson-Lindenstrauss (JL) theorem states that a set of points in high-dimensional space can be embedded into a lower-dimensional space while approximately preserving pairwise distances with high probability Johnson and Lindenstrauss…

数据结构与算法 · 计算机科学 2026-01-01 Pierre Mackenzie

The Johnson-Lindenstrauss Lemma (J-L Lemma) is a cornerstone of dimension reduction techniques. We study it in the one-bit context, namely we consider the unit sphere $ \mathbb S ^{N-1}$, with normalized geodesic metric, and map a finite…

泛函分析 · 数学 2019-03-07 Amadou Bah , Bryson Kagy , Emily Smith

Johnson--Lindenstrauss Transforms are powerful tools for reducing the dimensionality of data while preserving key characteristics of that data, and they have found use in many fields from machine learning to differential privacy and more.…

数据结构与算法 · 计算机科学 2021-03-02 Casper Benjamin Freksen

The Johnson-Lindenstrauss lemma allows dimension reduction on real vectors with low distortion on their pairwise Euclidean distances. This result is often used in algorithms such as $k$-means or $k$ nearest neighbours since they only use…

最优化与控制 · 数学 2015-07-06 Ky Vu , Pierre-Louis Poirion , Leo Liberti

Union of Subspaces (UoS) is a popular model to describe the underlying low-dimensional structure of data. The fine details of UoS structure can be described in terms of canonical angles (also known as principal angles) between subspaces,…

机器学习 · 计算机科学 2019-07-25 Yuchen Jiao , Gen Li , Yuantao Gu

In this paper, we consider robust optimization problems in high dimensions. Because a real-world dataset may contain significant noise or even specially crafted samples from some attacker, we are particularly interested in the optimization…

计算几何 · 计算机科学 2021-02-23 Hu Ding , Ruizhe Qin , Jiawei Huang

Dimension reduction is a key algorithmic tool with many applications including nearest-neighbor search, compressed sensing and linear algebra in the streaming model. In this work we obtain a {\em sparse} version of the fundamental tool in…

数据结构与算法 · 计算机科学 2015-03-14 Anirban Dasgupta , Ravi Kumar , Tamás Sarlós
‹ 上一页 1 2 3 10 下一页 ›