Results 11 to 20 of about 47,244 (191)
Revisiting Kernelized Locality-Sensitive Hashing for Improved Large-Scale Image Retrieval [PDF]
, 2014 We present a simple but powerful reinterpretation of kernelized locality-sensitive hashing (KLSH), a general and popular method developed in the vision community for performing approximate nearest-neighbor searches in an arbitrary reproducing kernel ...
Jiang, Ke, Kulis, Brian, Que, Qichao
core +1 more source
Embed and Conquer: Scalable Embeddings for Kernel k-Means on MapReduce [PDF]
, 2014 The kernel $k$-means is an effective method for data clustering which extends the commonly-used $k$-means algorithm to work on a similarity matrix over complex data structures.
Elgohary, Ahmed +3 more
core +1 more source
On non-normality and classification of amplification mechanisms in stability and resolvent analysis [PDF]
, 2017 We seek to quantify non-normality of the most amplified resolvent modes and predict their features based on the characteristics of the base or mean velocity profile.
Dawson, Scott T. M. +3 more
core +3 more sources
Average Characteristic Polynomials of Determinantal Point Processes [PDF]
, 2015 We investigate the average characteristic polynomial $\mathbb E\big[\prod_{i=1}^N(z-x_i)\big] $ where the $x_i$'s are real random variables which form a determinantal point process associated to a bounded projection operator.
Hardy, Adrien
core +2 more sources
Dimensionality Reduction Mappings [PDF]
, 2011 A wealth of powerful dimensionality reduction methods has been established which can be used for data visualization and preprocessing. These are accompanied by formal evaluation schemes, which allow a quantitative evaluation along general principles and ...
Biehl, Michael +3 more
core +2 more sources
Ridge Regression, Hubness, and Zero-Shot Learning
, 2015 This paper discusses the effect of hubness in zero-shot learning, when ridge regression is used to find a mapping between the example space to the label space.
Hara, Kazuo +4 more
core +1 more source
Point-wise Map Recovery and Refinement from Functional Correspondence [PDF]
, 2015 Since their introduction in the shape analysis community, functional maps have met with considerable success due to their ability to compactly represent dense correspondences between deformable shapes, with applications ranging from shape matching and ...
Cremers, Daniel +2 more
core +2 more sources
The Loss Rank Principle for Model Selection
, 2006 We introduce a new principle for model selection in regression and classification. Many regression models are controlled by some smoothness or flexibility or complexity parameter c, e.g.
A. Reusken +5 more
core +3 more sources
Randomized Dimension Reduction on Massive Data [PDF]
, 2013 Scalability of statistical estimators is of increasing importance in modern applications and dimension reduction is often used to extract relevant information from data.
Georgiev, Stoyan, Mukherjee, Sayan
core
, 2014 We propose here a first-principles, parameter free, real space method for the study of disordered extended defects in solids. We shall illustrate the power of the technique with an application to graphene sheets with randomly placed Stone-Wales defects ...
Baidya, Santu +8 more
core +1 more source