2 Search Results for "Li, Jerry"

Document
RANDOM
DOI: 10.4230/LIPIcs.APPROX/RANDOM.2021.35
The Product of Gaussian Matrices Is Close to Gaussian

Authors: Yi Li and David P. Woodruff

Published in: LIPIcs, Volume 207, Approximation, Randomization, and Combinatorial Optimization. Algorithms and Techniques (APPROX/RANDOM 2021)

Abstract
We study the distribution of the matrix product G₁ G₂ ⋯ G_r of r independent Gaussian matrices of various sizes, where G_i is d_{i-1} × d_i, and we denote p = d₀, q = d_r, and require d₁ = d_{r-1}. Here the entries in each G_i are standard normal random variables with mean 0 and variance 1. Such products arise in the study of wireless communication, dynamical systems, and quantum transport, among other places. We show that, provided each d_i, i = 1, …, r, satisfies d_i ≥ C p ⋅ q, where C ≥ C₀ for a constant C₀ > 0 depending on r, then the matrix product G₁ G₂ ⋯ G_r has variation distance at most δ to a p × q matrix G of i.i.d. standard normal random variables with mean 0 and variance ∏_{i = 1}^{r-1} d_i. Here δ → 0 as C → ∞. Moreover, we show a converse for constant r that if d_i < C' max{p,q}^{1/2}min{p,q}^{3/2} for some i, then this total variation distance is at least δ', for an absolute constant δ' > 0 depending on C' and r. This converse is best possible when p = Θ(q).
Cite as

Yi Li and David P. Woodruff. The Product of Gaussian Matrices Is Close to Gaussian. In Approximation, Randomization, and Combinatorial Optimization. Algorithms and Techniques (APPROX/RANDOM 2021). Leibniz International Proceedings in Informatics (LIPIcs), Volume 207, pp. 35:1-35:22, Schloss Dagstuhl – Leibniz-Zentrum für Informatik (2021)

Copy BibTex To Clipboard

@InProceedings{li_et_al:LIPIcs.APPROX/RANDOM.2021.35,
  author =	{Li, Yi and Woodruff, David P.},
  title =	{{The Product of Gaussian Matrices Is Close to Gaussian}},
  booktitle =	{Approximation, Randomization, and Combinatorial Optimization. Algorithms and Techniques (APPROX/RANDOM 2021)},
  pages =	{35:1--35:22},
  series =	{Leibniz International Proceedings in Informatics (LIPIcs)},
  ISBN =	{978-3-95977-207-5},
  ISSN =	{1868-8969},
  year =	{2021},
  volume =	{207},
  editor =	{Wootters, Mary and Sanit\`{a}, Laura},
  publisher =	{Schloss Dagstuhl -- Leibniz-Zentrum f{\"u}r Informatik},
  address =	{Dagstuhl, Germany},
  URL =		{https://drops-dev.dagstuhl.de/entities/document/10.4230/LIPIcs.APPROX/RANDOM.2021.35},
  URN =		{urn:nbn:de:0030-drops-147281},
  doi =		{10.4230/LIPIcs.APPROX/RANDOM.2021.35},
  annote =	{Keywords: random matrix theory, total variation distance, matrix product}
}
Document
DOI: 10.4230/LIPIcs.ESA.2021.61
Finding an Approximate Mode of a Kernel Density Estimate

Authors: Jasper C.H. Lee, Jerry Li, Christopher Musco, Jeff M. Phillips, and Wai Ming Tai

Published in: LIPIcs, Volume 204, 29th Annual European Symposium on Algorithms (ESA 2021)

Abstract
Given points P = {p₁,...,p_n} subset of ℝ^d, how do we find a point x which approximately maximizes the function 1/n ∑_{p_i ∈ P} e^{-‖p_i-x‖²}? In other words, how do we find an approximate mode of a Gaussian kernel density estimate (KDE) of P? Given the power of KDEs in representing probability distributions and other continuous functions, the basic mode finding problem is widely applicable. However, it is poorly understood algorithmically. We provide fast and provably accurate approximation algorithms for mode finding in both the low and high dimensional settings. For low (constant) dimension, our main contribution is a reduction to solving systems of polynomial inequalities. For high dimension, we prove the first dimensionality reduction result for KDE mode finding. The latter result leverages Johnson-Lindenstrauss projection, Kirszbraun’s classic extension theorem, and perhaps surprisingly, the mean-shift heuristic for mode finding. For constant approximation factor these algorithms run in O(n (log n)^{O(d)}) and O(nd + (log n)^{O(log³ n)}), respectively; these are proven more precisely as a (1+ε)-approximation guarantee. Furthermore, for the special case of d = 2, we give a combinatorial algorithm running in O(n log² n) time. We empirically demonstrate that the random projection approach and the 2-dimensional algorithm improves over the state-of-the-art mode-finding heuristics.
Cite as

Jasper C.H. Lee, Jerry Li, Christopher Musco, Jeff M. Phillips, and Wai Ming Tai. Finding an Approximate Mode of a Kernel Density Estimate. In 29th Annual European Symposium on Algorithms (ESA 2021). Leibniz International Proceedings in Informatics (LIPIcs), Volume 204, pp. 61:1-61:19, Schloss Dagstuhl – Leibniz-Zentrum für Informatik (2021)

Copy BibTex To Clipboard

@InProceedings{lee_et_al:LIPIcs.ESA.2021.61,
  author =	{Lee, Jasper C.H. and Li, Jerry and Musco, Christopher and Phillips, Jeff M. and Tai, Wai Ming},
  title =	{{Finding an Approximate Mode of a Kernel Density Estimate}},
  booktitle =	{29th Annual European Symposium on Algorithms (ESA 2021)},
  pages =	{61:1--61:19},
  series =	{Leibniz International Proceedings in Informatics (LIPIcs)},
  ISBN =	{978-3-95977-204-4},
  ISSN =	{1868-8969},
  year =	{2021},
  volume =	{204},
  editor =	{Mutzel, Petra and Pagh, Rasmus and Herman, Grzegorz},
  publisher =	{Schloss Dagstuhl -- Leibniz-Zentrum f{\"u}r Informatik},
  address =	{Dagstuhl, Germany},
  URL =		{https://drops-dev.dagstuhl.de/entities/document/10.4230/LIPIcs.ESA.2021.61},
  URN =		{urn:nbn:de:0030-drops-146428},
  doi =		{10.4230/LIPIcs.ESA.2021.61},
  annote =	{Keywords: Kernel density estimation, Dimensionality reduction, Coresets, Means-shift}
}
  • Refine by Author
  • 1 Lee, Jasper C.H.
  • 1 Li, Jerry
  • 1 Li, Yi
  • 1 Musco, Christopher
  • 1 Phillips, Jeff M.
  • Show More...

  • Refine by Classification
  • 1 Mathematics of computing → Probability and statistics
  • 1 Theory of computation → Design and analysis of algorithms

  • Refine by Keyword
  • 1 Coresets
  • 1 Dimensionality reduction
  • 1 Kernel density estimation
  • 1 Means-shift
  • 1 matrix product
  • Show More...

  • Refine by Type
  • 2 document

  • Refine by Publication Year
  • 2 2021

Questions / Remarks / Feedback
X

Feedback for Dagstuhl Publishing


Thanks for your feedback!

Feedback submitted

Could not send message

Please try again later or send an E-mail
© 2023-2024 Schloss Dagstuhl – LZI GmbH Imprint Privacy Contact