Search Results for author:
Found 19 papers, 6 papers with code
FastPart: Over-Parameterized Stochastic Gradient Descent for Sparse optimisation on Measures
This paper presents a novel algorithm that leverages Stochastic Gradient Descent strategies in conjunction with Random Features to augment the scalability of Conic Particle Gradient Descent (CPGD) specifically tailored for solving sparse optimisation problems on measures.
Neural Networks beyond explainability: Selective inference for sequence motifs
Over the past decade, neural networks have been successful at making predictions from biological sequences, especially in the context of regulatory genomics.
Three rates of convergence or separation via U-statistics in a dependent framework
Despite the ubiquity of U-statistics in modern Probability and Statistics, their non-asymptotic analysis in a dependent framework may have been overlooked.
Minimax Estimation of Partially-Observed Vector AutoRegressions
High-dimensional time series are a core ingredient of the statistical modeling toolkit, for which numerous estimation methods are known. But when observations are scarce or corrupted, the learning task becomes much harder. The question is: how much harder?
Towards Off-the-grid Algorithms for Total Variation Regularized Inverse Problems
We introduce an algorithm to solve linear inverse problems regularized with the total (gradient) variation in a gridless manner.
Forecasting Nonnegative Time Series via Sliding Mask Method (SMM) and Latent Clustered Forecast (LCF)
Based on recent advances in Nonnegative Matrix Factorization (NMF) and Archetypal Analysis, we introduce two procedures referred to as Sliding Mask Method (SMM) and Latent Clustered Forecast (LCF).
Concentration inequality for U-statistics of order two for uniformly ergodic Markov chains
We prove a new concentration inequality for U-statistics of order two for uniformly ergodic Markov chains.
Dual optimal design and the Christoffel-Darboux polynomial
The purpose of this short note is to show that the Christoffel-Darboux polynomial, useful in approximation theory and data science, arises naturally when deriving the dual to the problem of semi-algebraic D-optimal experimental design in statistics.
Optimization and Control Statistics Theory Statistics Theory
Markov Random Geometric Graph (MRGG): A Growth Model for Temporal Dynamic Networks
It is based on a Markovian latent space dynamic: consecutive latent points are sampled on the Euclidean Sphere using an unknown Markov kernel; and two nodes are connected with a probability depending on a unknown function of their latent geodesic distance.
Latent Distance Estimation for Random Geometric Graphs
We introduce a spectral estimator of the pairwise distance between latent points and we prove that its rate of convergence is the same as the nonparametric estimation of a function on $\mathbb{S}^{d-1}$, up to a logarithmic factor.
SuperMix: Sparse Regularization for Mixtures
This paper investigates the statistical estimation of a discrete mixing measure $\mu$0 involved in a kernel mixture model.
Nonnegative matrix factorization with side information for time series recovery and prediction
Motivated by the reconstruction and the prediction of electricity consumption, we extend Nonnegative Matrix Factorization~(NMF) to take into account side information (column or row features).
Nonnegative Matrix Factorization for Time Series Recovery From a Few Temporal Aggregates
Motivated by electricity consumption reconstitution, we propose a new matrix recovery method using nonnegative matrix factorization (NMF).
Approximate Optimal Designs for Multivariate Polynomial Regression
We introduce a new approach aiming at computing approximate optimal designs for multivariate polynomial regressions on compact (semi-algebraic) design spaces.
Statistics Theory Information Theory Information Theory Numerical Analysis Computation Methodology Statistics Theory 62K05, 90C25 (Primary) 41A10, 49M29, 90C90, 15A15 (secondary)
Testing Gaussian Process with Applications to Super-Resolution
This article introduces exact testing procedures on the mean of a Gaussian process $X$ derived from the outcomes of $\ell_1$-minimization over the space of complex valued measures.
Statistics Theory Information Theory Information Theory Probability Statistics Theory 62E15, 62F03, 60G15, 62H10, 62H15 (Primary) 60E05, 60G10, 62J05, 94A08 (secondary)
Recovering Multiple Nonnegative Time Series From a Few Temporal Aggregates
Motivated by electricity consumption metering, we extend existing nonnegative matrix factorization (NMF) algorithms to use linear measurements as observations, instead of matrix entries.
Sparse Recovery from Extreme Eigenvalues Deviation Inequalities
One benefit of this paper is a direct and explicit derivation of upper bounds on RICs and lower bounds on SRSR from small deviations on the extreme eigenvalues given by Random Matrix theory.
Reconstructing undirected graphs from eigenspaces
In this paper, we aim at recovering an undirected weighted graph of $N$ vertices from the knowledge of a perturbed version of the eigenspaces of its adjacency matrix $W$.
Optimal designs for Lasso and Dantzig selector using Expander Codes
We investigate the high-dimensional regression problem using adjacency matrices of unbalanced expander graphs.
