中文
相关论文

相关论文: A Unified Theory of Random Projection for Influenc…

200 篇论文

Random Projections have been widely used to generate embeddings for various graph learning tasks due to their computational efficiency. The majority of applications have been justified through the Johnson-Lindenstrauss Lemma. In this paper,…

社会与信息网络 · 计算机科学 2024-07-30 Tvrtko Tadić , Cassiano Becker , Jennifer Neville

Johnson-Lindenstrauss lemma states random projections can be used as a topology preserving embedding technique for fixed vectors. In this paper, we try to understand how random projections affect probabilistic properties of random vectors.…

概率论 · 数学 2022-07-26 JunTao Duan , Ionel Popescu , Fan Zhou

Random projections are random linear maps, sampled from appropriate distributions, that approx- imately preserve certain geometrical invariants so that the approximation improves as the dimension of the space grows. The well-known…

最优化与控制 · 数学 2017-06-12 Ky Vu , Pierre-Louis Poirion , Leo Liberti

The main contribution of the paper is to show that Gaussian sketching of a kernel-Gram matrix $\boldsymbol K$ yields an operator whose counterpart in an RKHS $\mathcal H$, is a \emph{random projection} operator---in the spirit of…

机器学习 · 统计学 2020-03-13 Samory Kpotufe , Bharath K. Sriperumbudur

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

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

Johnson-Lindenstrauss guarantees certain topological structure is preserved under random projections when project high dimensional deterministic vectors to low dimensional vectors. In this work, we try to understand how random matrix affect…

概率论 · 数学 2022-07-26 Juntao Duan , Ionel Popescu , Heinrich Matzinger

Interesting data often concentrate on low dimensional smooth manifolds inside a high dimensional ambient space. Random projections are a simple, powerful tool for dimensionality reduction of such data. Previous works have studied bounds on…

机器学习 · 统计学 2016-09-13 Subhaneil Lahiri , Peiran Gao , Surya Ganguli

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

This is a tutorial and survey paper on the Johnson-Lindenstrauss (JL) lemma and linear and nonlinear random projections. We start with linear random projection and then justify its correctness by JL lemma and its proof. Then, sparse random…

机器学习 · 统计学 2021-08-10 Benyamin Ghojogh , Ali Ghodsi , Fakhri Karray , Mark Crowley

For a tall $n\times d$ matrix $A$ and a random $m\times n$ sketching matrix $S$, the sketched estimate of the inverse covariance matrix $(A^\top A)^{-1}$ is typically biased: $E[(\tilde A^\top\tilde A)^{-1}]\ne(A^\top A)^{-1}$, where…

数据结构与算法 · 计算机科学 2021-07-13 Michał Dereziński , Zhenyu Liao , Edgar Dobriban , Michael W. Mahoney

Linear regression is a classic method of data analysis. In recent years, sketching -- a method of dimension reduction using random sampling, random projections, or both -- has gained popularity as an effective computational approximation…

机器学习 · 统计学 2020-08-04 Jocelyn T. Chi , Ilse C. F. Ipsen

The seminal result of Johnson and Lindenstrauss on random embeddings has been intensively studied in applied and theoretical computer science. Despite that vast body of literature, we still lack of complete understanding of statistical…

机器学习 · 计算机科学 2021-04-13 Maciej Skorski

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

There is an increasing body of work exploring the integration of random projection into algorithms for numerical linear algebra. The primary motivation is to reduce the overall computational cost of processing large datasets. A suitably…

数值分析 · 数学 2022-01-04 Daniel Ahfock , William J. Astle , Sylvia Richardson

We present a simplified and unified analysis of the Johnson-Lindenstrauss (JL) lemma, a cornerstone of dimensionality reduction for managing high-dimensional data. Our approach simplifies understanding and unifies various constructions…

机器学习 · 统计学 2024-07-22 Yingru Li

In this note we illustrate how common matrix approximation methods, such as random projection and random sampling, yield projection-cost-preserving sketches, as introduced in [FSS13, CEM+15]. A projection-cost-preserving sketch is a matrix…

数据结构与算法 · 计算机科学 2020-04-21 Cameron Musco , Christopher Musco

Sketch-and-project is a framework which unifies many known iterative methods for solving linear systems and their variants, as well as further extensions to non-linear optimization problems. It includes popular methods such as randomized…

最优化与控制 · 数学 2023-09-20 Michał Dereziński , Elizaveta Rebrova

Hierarchical inductive biases are hypothesized to promote generalizable policies in reinforcement learning, as demonstrated by explicit hyperbolic latent representations and architectures. Therefore, a more flexible approach is to have…

机器学习 · 计算机科学 2026-04-15 Tomohiro Hayase , Benoît Collins , Nakamasa Inoue

Rectified Flow (RF) models achieve state-of-the-art generation quality, yet controlling them for precise tasks -- such as semantic editing or blind image recovery -- remains a challenge. Current approaches bifurcate into inversion-based…

机器学习 · 计算机科学 2026-03-09 Vansh Bansal , James G Scott
‹ 上一页 1 2 3 10 下一页 ›