English
Related papers

Related papers: Sparse Hanson-Wright inequalities for subgaussian …

200 papers

We consider large-dimensional Hermitian or symmetric random matrices of the form $W=M+\vartheta V$ where $M$ is a Wigner matrix and $V$ is a real diagonal matrix whose entries are independent of $M$. For a large class of diagonal matrices…

Probability · Mathematics 2019-04-22 Hong Chang Ji , Ji Oon Lee

In this paper, we study the rate distortion function of the i.i.d sequence of multiplications of a Bernoulli $p$ random variable and a gaussian random variable $\sim N(0,1)$. We use a new technique in the derivation of the lower bound in…

Information Theory · Computer Science 2016-11-15 Cheng Chang

We consider the rate-distortion function for lossy source compression, as well as the channel capacity for error correction, through the lens of distributional robustness. We assume that the distribution of the source or of the additive…

Information Theory · Computer Science 2024-05-14 Vikrant Malik , Taylan Kargin , Victoria Kostina , Babak Hassibi

This work addresses the problem of high-dimensional classification by exploring the generalized Bayesian logistic regression method under a sparsity-inducing prior distribution. The method involves utilizing a fractional power of the…

Statistics Theory · Mathematics 2024-03-20 The Tien Mai

We show that any Littlewood--Paley square function $S$ satisfying a minimal local testing condition is dominated by a sparse form, \begin{equation*} \langle (Sf)^2,g \rangle\le C \sum_{I \in \mathscr{S}} \langle \lvert f\rvert\rangle_I^2…

Classical Analysis and ODEs · Mathematics 2020-11-03 Gianmarco Brocchi

In this work we propose and analyze a Hessian-based adaptive sparse quadrature to compute infinite-dimensional integrals with respect to the posterior distribution in the context of Bayesian inverse problems with Gaussian prior. Due to the…

Numerical Analysis · Mathematics 2018-02-14 Peng Chen , Umberto Villa , Omar Ghattas

We show bounds on tail probabilities for quadratic forms in sub-gaussian non-necessarily independent random variables. Our main tool will be estimates of the Luxemburg norms of such forms. This will allow us to formulate the above-mentioned…

Probability · Mathematics 2020-08-14 Krzysztof Zajkowski

Characteristic functions of weighted sums of independent random variables exhibit low-rank structure in the quantized tensor train (QTT) representation, also known as matrix product states (MPS), enabling up to exponential compression of…

Machine Learning · Statistics 2026-03-25 Juan José Rodríguez-Aldavero , Juan José García-Ripoll

The Lasso is an attractive technique for regularization and variable selection for high-dimensional data, where the number of predictor variables $p_n$ is potentially much larger than the number of samples $n$. However, it was recently…

Statistics Theory · Mathematics 2009-03-02 Nicolai Meinshausen , Bin Yu

The density of complex eigenvalues of random asymmetric $N\times N$ matrices is found in the large-$N$ limit. The matrices are of the form $H_0+A$ where $A$ is a matrix of $N^2$ independent, identically distributed random variables with…

Condensed Matter · Physics 2009-10-28 Boris A Khoruzhenko

Deep latent generative models have attracted increasing attention due to the capacity of combining the strengths of deep learning and probabilistic models in an elegant way. The data representations learned with the models are often…

Machine Learning · Computer Science 2023-04-04 Zhao Xu , Daniel Onoro Rubio , Giuseppe Serra , Mathias Niepert

We compute quantitative bounds for measuring the discrepancy between the distribution of two min-max statistics involving either pairs of Gaussian random matrices, or one Gaussian and one Gaussian-subordinated random matrix. In the fully…

Probability · Mathematics 2021-09-28 Giovanni Peccati , Nicola Turchi

We consider high-dimensional inference for potentially misspecified Cox proportional hazard models based on low dimensional results by Lin and Wei [1989]. A de-sparsified Lasso estimator is proposed based on the log partial likelihood…

Statistics Theory · Mathematics 2018-11-02 Shengchun Kong , Zhuqing Yu , Xianyang Zhang , Guang Cheng

We present a concentration result concerning random weighted projections in high dimensional spaces. As applications, we prove (1) New concentration inequalities for random quadratic forms; (2) The infinity norm of most unit eigenvectors of…

Probability · Mathematics 2014-08-19 Van Vu , Ke Wang

We study estimation of an $s$-sparse signal in the $p$-dimensional Gaussian sequence model with equicorrelated observations and derive the minimax rate. A new phenomenon emerges from correlation, namely the rate scales with respect to…

Statistics Theory · Mathematics 2025-01-23 Subhodh Kotekal , Chao Gao

Compressed sensing is a signal processing technique in which data is acquired directly in a compressed form. There are two modeling approaches that can be considered: the worst-case (Hamming) approach and a statistical mechanism, in which…

Information Theory · Computer Science 2016-01-20 Wasim Huleihel , Neri Merhav

We study the estimation of the covariance matrix $\Sigma$ of a $p$-dimensional normal random vector based on $n$ independent observations corrupted by additive noise. Only a general nonparametric assumption is imposed on the distribution of…

Statistics Theory · Mathematics 2018-03-28 Denis Belomestny , Mathias Trabs , Alexandre B. Tsybakov

High-dimensional auto-regressive models provide a natural way to model influence between $M$ actors given multi-variate time series data for $T$ time intervals. While there has been considerable work on network estimation, there is limited…

Statistics Theory · Mathematics 2018-12-13 Lili Zheng , Garvesh Raskutti

We generalize the heuristic parameter choice rule of Hanke-Raus for quadratic regularization to general variational regularization for solving linear as well as nonlinear ill-posed inverse problems in Banach spaces. Under source conditions…

Numerical Analysis · Mathematics 2016-08-03 Qinian Jin

Consider the product $X = X_{1}\cdots X_{m}$ of $m$ independent $n\times n$ iid random matrices. When $m$ is fixed and the dimension $n$ tends to infinity, we prove Gaussian limits for the centered linear spectral statistics of $X$ for…

Probability · Mathematics 2019-04-11 Natalie Coston , Sean O'Rourke