Bandwidth Selection in Kernel Density Estimation

By Hakon Kile. 2010

418 citations recorded by the source corpus.

View Paper: https://www.semanticscholar.org/paper/4daf05cc2c5e12fef6e69f1d5e412f4368a01729

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Citations in the corpus

Probabilistic Knowledge Transfer for Lightweight Deep Representation Learning (2020, background): “It is worth noting that several heuristics have been proposed to address speciﬁcally this limitation [41].”
Capital Allocation to Business Units and Sub-Portfolios: the Euler Principle (2007, background): “See, for instance, Turlach (1993) for an overview of this and other selection methods.”
Interval Estimation for Reinforcement-Learning Algorithms in Continuous-State Domains (2010, methodology): “Note that there are other bootstrapping techniques applicable to sequential, dependent data with lower coverage error, such as the double bootstrap [13], block-block bootstrap [1] and Markov or Sieve bootstrap [28].”
Bayesian Updating with Structural Reliability Methods (2015, methodology): “(25) Alternatively, kernel density approximations may be used for the posterior of 𝐗 or 𝑌(𝐗) (Turlach 1993).”
The Generalized Cross Entropy Method, with Applications to Probability Density Estimation (2011, unknown): “, [14], [39], [37], [52], [35], [59], [1]).”
Kernel density estimation and its application (2018, background): “parameters calculated for samples drawn from the same distribution is large [30].”
Robust kernel density estimation (2008, methodology): “For all experiments, we use the Gaussian kernel as the kernel function and the bandwidth is chosen as the least square crossvalidation estimator [9].”
Mutual Information Analysis: a Comprehensive Study (2011, methodology): “A number of approximation methods have been developed, see [32] for an extensive review.”
Beyond 5G With UAVs: Foundations of a 3D Wireless Cellular Network (2018, methodology): “We repeat this operation and take an average with L log-likelihood values, i.e., It can be shown [35], [36] that: and since we can ﬁnd h x , h y , and h z by a cross-validation method as: Hence, we can say that −L ( h x , h y , h z ) is a biased estimator of MISE.”
Background Subtraction for Freely Moving Cameras (2009, methodology): “In our experiments, the bandwidth was estimated using a likelihood cross-validation method [31] with weights proportional to the k nearest neighbors, where k = √ n.”
Learning Deep Representations with Probabilistic Knowledge Transfer (2018, background): “This is not a straightforward task, with several heuristics proposed to tackle this problem [46].”