random projections
Quadratic polynomial kernel approximation with asymmetric embeddings
Abstract: Random embedding techniques, such as random Fourier features, are widely used to sketch initial data to a new, kernelised feature space. In this work, we leverage a specific property of random rank-one projection operators, the sign product embedding, to approximate a quadratic polynomial kernel using the scalar product of a pair asymmetric vector embeddings, with one taking only binary values.
Breaking the waves: asymmetric random periodic features for low-bitrate kernel machines
Abstract: Many signal processing and machine learning applications are built from evaluating a kernel on pairs of signals, e.g. to assess the similarity of an incoming query to a database of known signals.
Through the Haze: a Non-Convex Approach to Blind Gain Calibration for Linear Random Sensing Models
Abstract: Computational sensing strategies often suffer from calibration errors in the physical implementation of their ideal sensing models. Such uncertainties are typically addressed by using multiple, accurately chosen training signals to recover the missing information on the sensing model, an approach that can be resource-consuming and cumbersome.
The Rare Eclipse Problem on Tiles: Quantized Embeddings of Disjoint Convex Sets
(joint work with V. Cambareri and C. Xu). See also arXiv:1702.04664 for the corresponding preprint.
Time for dithering: fast and quantized random embeddings via the restricted isometry property
Abstract: Recently, many works have focused on the characterization of non-linear dimensionality reduction methods obtained by quantizing linear embeddings, e.g., to reach fast processing time, efficient data compression procedures, novel geometry-preserving embeddings or to estimate the information/bits stored in this reduced data representation.
Quantized random projections of low-complexity sets
2016 Invited speaker, talk on “”.
Consistent Basis Pursuit for Signal and Matrix Estimates in Quantized Compressed Sensing
Abstract: This paper focuses on the estimation of low-complexity signals when they are observed through \(M\) uniformly quantized compressive observations. Among such signals, we consider 1-D sparse vectors, low-rank matrices, or compressible signals that are well approximated by one of these two models.
Quasi-isometric embeddings of vector sets with quantized sub-Gaussian projections
Last January, I was honored to be invited in RWTH Aachen University by Holger Rauhut and Sjoerd Dirksen to give a talk on the general topic of quantized compressed sensing. In particular, I decided to focus my presentation on the quasi-isometric embeddings arising in 1-bit compressed sensing, as developed by a few researchers in this field (e.
Quasi-isometric embeddings of vector sets with quantized sub-Gaussian projections
\(\newcommand{\cl}{\mathcal}\newcommand{\bb}{\mathbb}%\)
Last January, I was honored to be invited in RWTH Aachen University by Holger Rauhut and Sjoerd Dirksen to give a talk on the general topic of quantized compressed sensing.
