English
Related papers

Related papers: Componentwise condition numbers of random sparse m…

200 papers

We present upper and lower bounds for the prediction error of the Lasso. For the case of random Gaussian design, we show that under mild conditions the prediction error of the Lasso is up to smaller order terms dominated by the prediction…

Statistics Theory · Mathematics 2018-04-04 Sara van de Geer

We compare Stochastic and Worst-case condition numbers and loss of precision for general computational problems. We show an upper bound for the ratio of Worst-case condition number to the Stochastic condition number of order O(sqrt m). We…

Numerical Analysis · Mathematics 2008-12-25 Dennis Cheung , Lisa H. Y. Zhou

We derive a finite-sample probabilistic bound on the parameter estimation error of a system identification algorithm for Linear Switched Systems. The algorithm estimates Markov parameters from a single trajectory and applies a variant of…

Machine Learning · Computer Science 2025-05-19 Daniel Racz , Mihaly Petreczky , Balint Daroczy

We develop a theoretical approach to compute the conditioned spectral density of $N \times N$ non-invariant random matrices in the limit $N \rightarrow \infty$. This large deviation observable, defined as the eigenvalue distribution…

Disordered Systems and Neural Networks · Physics 2018-08-15 Isaac Pérez Castillo , Fernando L. Metz

The goal of predictive sparse coding is to learn a representation of examples as sparse linear combinations of elements from a dictionary, such that a learned hypothesis linear in the new representation performs well on a predictive task.…

Machine Learning · Computer Science 2012-10-09 Nishant A. Mehta , Alexander G. Gray

We consider marginal log-linear models for parameterizing distributions on multidimensional contingency tables. These models generalize ordinary log-linear and multivariate logistic models, besides several others. First, we obtain some…

Statistics Theory · Mathematics 2019-10-25 S. Ghosh , P. Vellaisamy

We consider the problem of finding a low discrepancy coloring for sparse set systems where each element lies in at most $t$ sets. We give an algorithm that finds a coloring with discrepancy $O((t \log n \log s)^{1/2})$ where $s$ is the…

Data Structures and Algorithms · Computer Science 2016-02-03 Nikhil Bansal , Shashwat Garg

This paper considers the problem of matrix-variate logistic regression. It derives the fundamental error threshold on estimating low-rank coefficient matrices in the logistic regression problem by obtaining a lower bound on the minimax…

Machine Learning · Computer Science 2022-05-10 Batoul Taki , Mohsen Ghassemi , Anand D. Sarwate , Waheed U. Bajwa

In this article, we discuss the composite likelihood estimation of sparse Gaussian graphical models. When there are symmetry constraints on the concentration matrix or partial correlation matrix, the likelihood estimation can be…

Computation · Statistics 2012-08-22 Xin Gao , Helene Massam

We consider the rate of convergence of the expected loss of empirically optimal vector quantizers. Earlier results show that the mean-squared expected distortion for any fixed distribution supported on a bounded set and satisfying some…

Statistics Theory · Mathematics 2012-02-01 Clément Levrard

Sparse linear regression with ill-conditioned Gaussian random designs is widely believed to exhibit a statistical/computational gap, but there is surprisingly little formal evidence for this belief, even in the form of examples that are…

Data Structures and Algorithms · Computer Science 2022-03-08 Jonathan A. Kelner , Frederic Koehler , Raghu Meka , Dhruv Rohatgi

We show that coarse graining arguments invented for the analysis of multi-spin systems on a randomly triangulated surface apply also to the O(n) model on a random lattice. These arguments imply that if the model has a critical point with…

High Energy Physics - Theory · Physics 2009-10-30 B. Durhuus , C. Kristjansen

We prove an L2 recovery bound for a family of sparse estimators defined as minimizers of some empirical loss functions -- which include hinge loss and logistic loss. More precisely, we achieve an upper-bound for coefficients estimation…

Statistics Theory · Mathematics 2019-01-15 Antoine Dedieu

We consider the problem of finding a low discrepancy coloring for sparse set systems where each element lies in at most t sets. We give an efficient algorithm that finds a coloring with discrepancy O((t log n)^{1/2}), matching the best…

Data Structures and Algorithms · Computer Science 2016-09-13 Nikhil Bansal , Daniel Dadush , Shashwat Garg

Compressed sensing and its extensions have recently triggered interest in randomized signal acquisition. A key finding is that random measurements provide sparse signal reconstruction guarantees for efficient and stable algorithms with a…

Information Theory · Computer Science 2014-07-08 Felix Krahmer , Holger Rauhut

Low-rank tensor approximation error bounds are proposed for the case of noisy input data that depend on low-rank representation type, rank and the dimensionality of the tensor. The bounds show that high-dimensional low-rank structured…

Numerical Analysis · Mathematics 2024-12-16 Sergey Petrov , Nikolai Zamarashkin

In the context of the compressed sensing problem, we propose a new ensemble of sparse random matrices which allow one (i) to acquire and compress a {\rho}0-sparse signal of length N in a time linear in N and (ii) to perfectly recover the…

Information Theory · Computer Science 2013-04-15 Maria Chiara Angelini , Federico Ricci-Tersenghi , Yoshiyuki Kabashima

We prove an algorithmic regularity lemma for $L_p$ regular matrices $(1 < p \leq \infty),$ a class of sparse $\{0,1\}$ matrices which obey a natural pseudorandomness condition. This extends a result of Coja-Oghlan, Cooper and Frieze who…

Combinatorics · Mathematics 2017-05-19 Thodoris Karageorgos , Silouanos Brazitikos

We deal with the random combinatorial structures called assemblies. By weakening the logarithmic condition which assures regularity of the number of components of a given order, we extend the notion of logarithmic assemblies. Using the…

Probability · Mathematics 2009-03-06 Eugenijus Manstavičius

We improve existing results in the field of compressed sensing and matrix completion when sampled data may be grossly corrupted. We introduce three new theorems. 1) In compressed sensing, we show that if the m \times n sensing matrix has…

Information Theory · Computer Science 2012-01-19 Xiaodong Li