Zobrazeno 1 - 10
of 60
pro vyhledávání: '"Rebrova, Elizaveta"'
Autor:
Chaudhry, Abraar, Rebrova, Elizaveta
We propose a flexible and theoretically supported framework for scalable nonnegative matrix factorization. The goal is to find nonnegative low-rank components directly from compressed measurements, accessing the original data only once or twice. We c
Externí odkaz:
http://arxiv.org/abs/2409.04994
A fundamental problem in machine learning is understanding the effect of early stopping on the parameters obtained and the generalization capabilities of the model. Even for linear models, the effect is not fully understood for arbitrary learning rat
Externí odkaz:
http://arxiv.org/abs/2406.04425
We study the discrete dynamics of mini-batch gradient descent for least squares regression when sampling without replacement. We show that the dynamics and generalization error of mini-batch gradient descent depends on a sample cross-covariance matri
Externí odkaz:
http://arxiv.org/abs/2406.03696
While effective in practice, iterative methods for solving large systems of linear equations can be significantly affected by problem-dependent condition number quantities. This makes characterizing their time complexity challenging, particularly whe
Externí odkaz:
http://arxiv.org/abs/2405.05818
We propose SGD-exp, a stochastic gradient descent approach for linear and ReLU regressions under Massart noise (adversarial semi-random corruption model) for the fully streaming setting. We show novel nearly linear convergence guarantees of SGD-exp t
Externí odkaz:
http://arxiv.org/abs/2403.01204
Autor:
Lok, Jackie, Rebrova, Elizaveta
We study a version of the randomized Kaczmarz algorithm for solving systems of linear equations where the iterates are confined to the solution space of a selected subsystem. We show that the subspace constraint leads to an accelerated convergence ra
Externí odkaz:
http://arxiv.org/abs/2309.04889
In this paper we consider the problem of recovering a low-rank Tucker approximation to a massive tensor based solely on structured random compressive measurements. Crucially, the proposed random measurement ensembles are both designed to be compactly
Externí odkaz:
http://arxiv.org/abs/2308.13709
When solving noisy linear systems Ax = b + c, the theoretical and empirical performance of stochastic iterative methods, such as the Randomized Kaczmarz algorithm, depends on the noise level. However, if there are a small number of highly corrupt mea
Externí odkaz:
http://arxiv.org/abs/2308.07987
Autor:
Rebrova, Elizaveta, Salanevich, Palina
Uncertainty principles present an important theoretical tool in signal processing, as they provide limits on the time-frequency concentration of a signal. In many real-world applications the signal domain has a complicated irregular structure that ca
Externí odkaz:
http://arxiv.org/abs/2306.15810
Autor:
Dereziński, Michał, Rebrova, Elizaveta
Sketch-and-project is a framework which unifies many known iterative methods for solving linear systems and their variants, as well as further extensions to non-linear optimization problems. It includes popular methods such as randomized Kaczmarz, co
Externí odkaz:
http://arxiv.org/abs/2208.09585