Statistical limits of dictionary learning: Random matrix theory and the spectral replica method
Graph Chatbot
Chat with Graph Search
Ask any question about EPFL courses, lectures, exercises, research, news, etc. or try the example questions below.
DISCLAIMER: The Graph Chatbot is not programmed to provide explicit or categorical answers to your questions. Rather, it transforms your questions into API requests that are distributed across the various IT services officially administered by EPFL. Its purpose is solely to collect and recommend relevant references to content that you can explore to help you answer your questions.
We investigate a stochastic signal-processing framework for signals with sparse derivatives, where the samples of a Levy process are corrupted by noise. The proposed signal model covers the well-known Brownian motion and piecewise-constant Poisson process; ...
In this work we consider the problem of approximating the statistics of a given Quantity of Interest (QoI) that depends on the solution of a linear elliptic PDE defined over a random domain parameterized by N random variables. The elliptic problem is remap ...
An alternative way to process data from polarization measurements for fuel cell model validation is proposed. The method is based on re- and subsampling of IV data, with which repetitive estimations are obtained for the model parameters. This way statistic ...
We present tracial analogs of the classical results of Curto and Fialkow on moment matrices. A sequence of real numbers indexed by words in noncommuting variables with values invariant under cyclic permutations of the indexes, is called a tracial sequence. ...
This report addresses the problem of speech enhancement employing the Minimum Mean-Square Error (MMSE) of β-order Short Time Spectral Amplitude (STSA). We present an analytical solution for β-order MMSE estimator where Discrete Fourier Transform (DFT) coef ...
The ClearPEM is a dedicated APD-based PET detector for high-resolution breast cancer imaging. The detector module is composed of 12 LYSO:Ce crystal matrices, each with 4 x 8 individual crystals (2 x 2 x 20 mm(3)) optically coupled on both ends to S8550 Ham ...
Distributed Constraint Satisfaction (DisCSP) and Distributed Constraint Optimization (DCOP) are formal frameworks that can be used to model a variety of problems in which multiple decision-makers cooperate towards a common goal: from computing an equilibri ...
Although neural substrates of mammalian female mating behavior have been described [1, 2], the association between complex courtship activity and specific underlying mechanisms remains elusive [3]. We have isolated a mouse line that unexpectedly shows alte ...
Assume a multichannel data matrix, which due to the column-wise dependencies, has low-rank and joint-sparse representation. This matrix wont have many degrees of freedom. Enormous developments over the last decade in areas of compressed sensing and low-ran ...
In this work, we derive a near-optimal combination rule for adaptation over networks. To do so, we first establish a useful result pertaining to the steady-state distribution of the estimator of an LMS filter. Specifically, under small step-sizes and some ...
