Search Results for author: Valeriya Naumova

Found 6 papers, 2 papers with code

StreaMRAK a Streaming Multi-Resolution Adaptive Kernel Algorithm

no code implementations23 Aug 2021 Andreas Oslandsbotn, Zeljko Kereta, Valeriya Naumova, Yoav Freund, Alexander Cloninger

With a novel sub-sampling scheme, StreaMRAK reduces memory and computational complexities by creating a sketch of the original data, where the sub-sampling density is adapted to the bandwidth of the kernel and the local dimensionality of the data.

Computational approaches to non-convex, sparsity-inducing multi-penalty regularization

no code implementations7 Aug 2019 Zeljko Kereta, Johannes Maly, Valeriya Naumova

In this work we consider numerical efficiency and convergence rates for solvers of non-convex multi-penalty formulations when reconstructing sparse signals from noisy linear measurements.

Information Theory Information Theory

Nonlinear generalization of the monotone single index model

1 code implementation24 Feb 2019 Zeljko Kereta, Timo Klock, Valeriya Naumova

This paper deals with a nonlinear generalization of this framework to allow for a regressor that uses multiple index vectors, adapting to local changes in the responses.


Robust Recovery of Low-Rank Matrices with Non-Orthogonal Sparse Decomposition from Incomplete Measurements

no code implementations18 Jan 2018 Massimo Fornasier, Johannes Maly, Valeriya Naumova

By adapting the concept of restricted isometry property from compressed sensing to our novel model class, we prove error bounds between global minimizers and ground truth, up to noise level, from a number of subgaussian measurements scaling as $R(s_1+s_2)$, up to log-factors in the dimension, and relative-to-diameter distortion.

Numerical Analysis Numerical Analysis

Adaptive multi-penalty regularization based on a generalized Lasso path

1 code implementation11 Oct 2017 Markus Grasmair, Timo Klock, Valeriya Naumova

Another advantage of our algorithm is that it provides an overview on the solution stability over the whole range of parameters.

Model Selection

Dictionary Learning from Incomplete Data

no code implementations13 Jan 2017 Valeriya Naumova, Karin Schnass

This paper extends the recently proposed and theoretically justified iterative thresholding and $K$ residual means algorithm ITKrM to learning dicionaries from incomplete/masked training data (ITKrMM).

Dictionary Learning Image Inpainting

Cannot find the paper you are looking for? You can Submit a new open access paper.