English
Related papers

Related papers: Noise Regularizes Over-parameterized Rank One Matr…

200 papers

Deep learning methods operate in regimes that defy the traditional statistical mindset. Neural network architectures often contain more parameters than training samples, and are so rich that they can interpolate the observed labels, even if…

Statistics Theory · Mathematics 2020-12-14 Song Mei , Andrea Montanari

We consider the following signal recovery problem: given a measurement matrix $\Phi\in \mathbb{R}^{n\times p}$ and a noisy observation vector $c\in \mathbb{R}^{n}$ constructed from $c = \Phi\theta^* + \epsilon$ where $\epsilon\in…

Machine Learning · Statistics 2013-07-23 Ji Liu , Lei Yuan , Jieping Ye

Variational quantum algorithms rely on the optimization of parameterized quantum circuits in noisy settings. The commonly used back-propagation procedure in classical machine learning is not directly applicable in this setting due to the…

Quantum Physics · Physics 2024-08-27 Zhiyan Ding , Taehee Ko , Jiahao Yao , Lin Lin , Xiantao Li

A host of problems involve the recovery of structured signals from a dimensionality reduced representation such as a random projection; examples include sparse signals (compressive sensing) and low-rank matrices (matrix completion). Given…

Information Theory · Computer Science 2012-05-22 Shirin Jalali , Arian Maleki , Richard Baraniuk

Reduced-rank approach has been used for decades in robust linear estimation of both deterministic and random vector of parameters in linear model y=Hx+\sqrt{epsilon}n. In practical settings, estimation is frequently performed under…

Optimization and Control · Mathematics 2024-08-05 Tomasz Piotrowski , Isao Yamada

Optimization of sensor selection has been studied to monitor complex and large-scale systems with data-driven linear reduced-order modeling. An algorithm for greedy sensor selection is presented under the assumption of correlated noise in…

Signal Processing · Electrical Eng. & Systems 2022-07-14 Keigo Yamada , Yuji Saito , Taku Nonomura , Keisuke Asai

Overparameterization is known to permit strong generalization performance in neural networks. In this work, we provide an initial theoretical analysis of its effect on catastrophic forgetting in a continual learning setup. We show…

Machine Learning · Computer Science 2022-07-15 Daniel Goldfarb , Paul Hand

We develop a multidimensional version of Gradient-MUSIC for estimating the frequencies of a nonharmonic signal from noisy samples. The guiding principle is that frequency recovery should be based only on the signal subspace determined by…

Optimization and Control · Mathematics 2026-03-31 Albert Fannjiang , Weilin Li

In this paper we study the problem of learning a shallow artificial neural network that best fits a training data set. We study this problem in the over-parameterized regime where the number of observations are fewer than the number of…

Machine Learning · Computer Science 2022-08-25 Mahdi Soltanolkotabi , Adel Javanmard , Jason D. Lee

Randomly perturbing networks during the training process is a commonly used approach to improving generalization performance. In this paper, we present a theoretical study of one particular way of random perturbation, which corresponds to…

Machine Learning · Computer Science 2021-02-16 Oussama Dhifallah , Yue M. Lu

We present a strategy for the recovery of a sparse solution of a common problem in acoustic engineering, which is the reconstruction of sound source levels and locations applying microphone array measurements. The considered task bears…

Optimization and Control · Mathematics 2016-07-04 Laurent Hoeltgen , Michael Breuß , Gert Herold , Ennes Sarradj

Mathematically characterizing the implicit regularization induced by gradient-based optimization is a longstanding pursuit in the theory of deep learning. A widespread hope is that a characterization based on minimization of norms may…

Machine Learning · Computer Science 2020-10-20 Noam Razin , Nadav Cohen

We study the problem of recovering an incomplete $m\times n$ matrix of rank $r$ with columns arriving online over time. This is known as the problem of life-long matrix completion, and is widely applied to recommendation system, computer…

Machine Learning · Computer Science 2016-12-04 Maria-Florina Balcan , Hongyang Zhang

In deep learning it is common to overparameterize neural networks, that is, to use more parameters than training samples. Quite surprisingly training the neural network via (stochastic) gradient descent leads to models that generalize very…

Optimization and Control · Mathematics 2025-01-30 Hung-Hsu Chou , Johannes Maly , Holger Rauhut

We consider recovery of low-rank matrices from noisy data by shrinkage of singular values, in which a single, univariate nonlinearity is applied to each of the empirical singular values. We adopt an asymptotic framework, in which the matrix…

Statistics Theory · Mathematics 2016-05-17 Matan Gavish , David L. Donoho

Magnetic particle imaging reconstructs tracer distributions using a system matrix obtained through time-consuming, noise-prone calibration measurements. Methods for addressing imperfections in measured system matrices increasingly rely on…

Image and Video Processing · Electrical Eng. & Systems 2026-03-20 Artyom Tsanda , Sarah Reiss , Konrad Scheffler , Marija Boberg , Tobias Knopp

Due to measurement noise, a common problem in in various fields is how to estimate the ratio of two functions. We consider this problem of estimating the ratio of two functions in a nonparametric regression model. Assuming the noise is…

Methodology · Statistics 2013-11-28 Jelena Markovic , Lie Wang

In recent years, there is a growing need for processing methods aimed at extracting useful information from large datasets. In many cases the challenge is to discover a low-dimensional structure in the data, often concealed by the existence…

Statistics Theory · Mathematics 2019-06-05 Yariv Aizenbud , Boris Landa , Yoel Shkolnisky

For random matrix models, the parameter estimation based on the traditional likelihood functions is not straightforward in particular when we have only one sample matrix. We introduce a new parameter optimization method for random matrix…

Machine Learning · Statistics 2021-06-07 Tomohiro Hayase

Temporal Difference (TD) algorithms are widely used in Deep Reinforcement Learning (RL). Their performance is heavily influenced by the size of the neural network. While in supervised learning, the regime of over-parameterization and its…

Machine Learning · Computer Science 2024-02-20 David Brellmann , Eloïse Berthier , David Filliat , Goran Frehse