English
Related papers

Related papers: Smoothed analysis in compressed sensing

200 papers

We give a proof of the conjecture of Nelson and Nguyen [FOCS 2013] on the optimal dimension and sparsity of oblivious subspace embeddings, up to sub-polylogarithmic factors: For any $n\geq d$ and $\epsilon\geq d^{-O(1)}$, there is a random…

Data Structures and Algorithms · Computer Science 2025-11-18 Shabarish Chenakkod , Michał Dereziński , Xiaoyu Dong

As the popularity of deep learning (DL) in the field of magnetic resonance imaging (MRI) continues to rise, recent research has indicated that DL-based MRI reconstruction models might be excessively sensitive to minor input disturbances,…

Image and Video Processing · Electrical Eng. & Systems 2025-10-07 Shijun Liang , Van Hoang Minh Nguyen , Jinghan Jia , Ismail Alkhouri , Sijia Liu , Saiprasad Ravishankar

Recent studies on deep neural networks show that flat minima of the loss landscape correlate with improved generalization. Sharpness-aware minimization (SAM) efficiently finds flat regions by updating the parameters according to the…

Machine Learning · Computer Science 2025-02-13 Albert Kjøller Jacobsen , Georgios Arvanitidis

We prove novel algorithmic guarantees for several online problems in the smoothed analysis model. In this model, at each time an adversary chooses an input distribution with density function bounded above by $\tfrac{1}{\sigma}$ times that…

Machine Learning · Computer Science 2021-08-20 Nika Haghtalab , Tim Roughgarden , Abhishek Shetty

Smooth linear statistics of random permutation matrices, sampled under a general Ewens distribution, exhibit an interesting non-universality phenomenon. Though they have bounded variance, their fluctuations are asymptotically non-Gaussian…

Probability · Mathematics 2011-06-13 Gérard Ben Arous , Kim Dang

We consider the problem of finite-time identification of linear dynamical systems from $T$ samples of a single trajectory. Recent results have predominantly focused on the setup where either no structural assumption is made on the system…

Statistics Theory · Mathematics 2025-10-02 Hemant Tyagi , Denis Efimov

Structural Nested Mean Models (SNMMs) are useful for causal inference of treatment effects in longitudinal observational studies. Most existing works assume that the data are collected at pre-fixed time points for all subjects, which,…

Methodology · Statistics 2020-01-13 Shu Yang

We present improved sampling complexity bounds for stable and robust sparse recovery in compressed sensing. Our unified analysis based on l1 minimization encompasses the case where (i) the measurements are block-structured samples in order…

Information Theory · Computer Science 2020-05-22 Ben Adcock , Claire Boyer , Simone Brugiapaglia

Randomized smoothing has shown promising certified robustness against adversaries in classification tasks. Despite such success with only zeroth-order access to base models, randomized smoothing has not been extended to a general form of…

Machine Learning · Computer Science 2024-05-16 Aref Miri Rekavandi , Olga Ohrimenko , Benjamin I. P. Rubinstein

The main paradigm of smoothed analysis on graphs suggests that for any large graph $G$ in a certain class of graphs, perturbing slightly the edges of $G$ at random (usually adding few random edges to $G$) typically results in a graph having…

Combinatorics · Mathematics 2015-08-13 Michael Krivelevich , Daniel Reichman , Wojciech Samotij

In the first part of this paper, we show that the small-ball condition, recently introduced by Mendelson (2015), may behave poorly for important classes of localized functions such as wavelets, piecewise polynomials or trigonometric…

Statistics Theory · Mathematics 2016-10-19 Adrien Saumard

Recent research has studied the role of sparsity in high dimensional regression and signal reconstruction, establishing theoretical limits for recovering sparse models from sparse data. This line of work shows that $\ell_1$-regularized…

Machine Learning · Statistics 2012-01-11 Shuheng Zhou , John Lafferty , Larry Wasserman

Since Shannon's foundational work, rate-distortion theory has defined the fundamental limits of lossy compression. Classical results, derived for memoryless and stationary ergodic sources in the asymptotic regime, have shaped both transform…

Information Theory · Computer Science 2026-03-11 Sujata Sinha , Vishwas Rao , Robert Underwood , David Lenz , Sheng Di , Franck Cappello , Lingjia Liu

With some regularity conditions maximum likelihood estimators (MLEs) always produce asymptotically optimal (in the sense of consistency, efficiency, sufficiency, and unbiasedness) estimators. But in general, the MLEs lead to non-robust…

Methodology · Statistics 2024-02-22 Chudamani Poudyal

Several recent randomized linear algebra algorithms rely upon fast dimension reduction methods. A popular choice is the Subsampled Randomized Hadamard Transform (SRHT). In this article, we address the efficacy, in the Frobenius and spectral…

Data Structures and Algorithms · Computer Science 2015-03-20 Christos Boutsidis , Alex Gittens

Given a family $(\mu_\lambda,\lambda\geq0)$ of integrable mean-zero probability measures such that, for every $\lambda\geq0$, $\mu_\lambda$ is the image of $\mu_1$ under the homothety $y\longmapsto\sqrt{\lambda}y$, we provide a necessary…

Probability · Mathematics 2019-06-20 Antoine-Marie Bogso , Mbehou Mohamed

Tremendous efforts have been made to study the theoretical and algorithmic aspects of sparse recovery and low-rank matrix recovery. This paper fills a theoretical gap in matrix recovery: the optimal sample complexity for stable recovery…

Information Theory · Computer Science 2017-12-27 Yanjun Li , Kiryung Lee , Yoram Bresler

Tremendous efforts have been made to study the theoretical and algorithmic aspects of sparse recovery and low-rank matrix recovery. This paper fills a theoretical gap in matrix recovery: the optimal sample complexity for stable recovery…

Information Theory · Computer Science 2018-01-03 Yanjun Li , Kiryung Lee , Yoram Bresler

Performance of regularized least-squares estimation in noisy compressed sensing is analyzed in the limit when the dimensions of the measurement matrix grow large. The sensing matrix is considered to be from a class of random ensembles that…

Information Theory · Computer Science 2016-02-08 Mikko Vehkapera , Yoshiyuki Kabashima , Saikat Chatterjee

Compressive sensing predicts that sufficiently sparse vectors can be recovered from highly incomplete information. Efficient recovery methods such as $\ell_1$-minimization find the sparsest solution to certain systems of equations. Random…

Information Theory · Computer Science 2011-08-17 Ulaş Ayaz , Holger Rauhut