no code implementations • 12 Feb 2025 • Joseph Gabet, Meghna Kalra, Maxime Ferreira Da Costa, Kiryung Lee
Spike deconvolution is the problem of recovering point sources from their convolution with a known point spread function, playing a fundamental role in many sensing and imaging applications.
no code implementations • 4 Nov 2024 • Haitham Kanj, Seonho Kim, Kiryung Lee
When the model order and parameters are fixed, Sp-GD provides an $\epsilon$-accurate estimate given $\mathcal{O}(\max(\epsilon^{-2}\sigma_z^2, 1)s\log(d/s))$ observations where $\sigma_z^2$ denotes the noise variance.
no code implementations • 5 Mar 2024 • Meghna Kalra, Maxime Ferreira Da Costa, Kiryung Lee
In the small noise regime, the local Lipschitz constant converges to the spectral norm of the noiseless Jacobian of the inverse map.
no code implementations • 30 Aug 2023 • Meghna Kalra, Kiryung Lee
ESPRIT algorithm has been used to estimate the pulse locations.
no code implementations • 15 Aug 2023 • Seonho Kim, Kiryung Lee
We consider regression of a max-affine model that produces a piecewise linear model by combining affine models via the max function.
no code implementations • 25 Apr 2022 • Kiryung Lee, Dominik Stöger
In this paper, we show that ALS with random initialization converges to the true solution with $\varepsilon$-accuracy in $O(\log n + \log (1/\varepsilon)) $ iterations using only a near-optimal amount of samples, where we assume the measurement matrices to be i. i. d.
no code implementations • 12 Mar 2021 • Seonho Kim, Sohail Bahmani, Kiryung Lee
When the $k$ linear components are equally likely to achieve the maximum, our result shows a sufficient number of noise-free observations for exact recovery scales as {$k^{4}p$} up to a logarithmic factor.
no code implementations • 6 Apr 2020 • Sohail Bahmani, Kiryung Lee
We study an estimator with a convex formulation for recovery of low-rank matrices from rank-one projections.
1 code implementation • 8 Feb 2020 • Shen Zhao, Lee C. Potter, Kiryung Lee, Rizwan Ahmad
Magnetic Resonance Imaging (MRI) is a noninvasive imaging technique that provides exquisite soft-tissue contrast without using ionizing radiation.
no code implementations • NeurIPS 2019 • Rakshith Sharma Srinivasa, Kiryung Lee, Marius Junge, Justin Romberg
We address a low-rank matrix recovery problem where each column of a rank-r matrix X of size (d1, d2) is compressed beyond the point of recovery to size L with L << d1.
no code implementations • 30 Nov 2017 • Yanjun Li, Kiryung Lee, Yoram Bresler
We also show that our power iteration algorithms for BGPC compare favorably with competing algorithms in adversarial conditions, e. g., with noisy measurement or with a bad initial estimate.
no code implementations • 28 Jun 2017 • Marius Junge, Kiryung Lee
The restricted isometry property (RIP) is a universal tool for data recovery.
no code implementations • 28 Jun 2017 • Marius Junge, Kiryung Lee
The restricted isometry property (RIP) is an integral tool in the analysis of various inverse problems with sparsity models.