paper-with-me

홈 › Papers

Polynomial-time Sparse Measure Recovery: From Mean Field Theory to Algorithm Design

2022-04-16 · Hadi Daneshmand, Francis Bach

Mean field theory has provided theoretical insights into various algorithms by letting the problem size tend to infinity. We argue that the applications of mean-field theory go beyond theoretical insights as it can inspire the design of practical algorithms. Leveraging mean-field analyses in physics, we propose a novel algorithm for sparse measure recovery. For sparse measures over $\mathbb{R}$, we propose a polynomial-time recovery method from Fourier moments that improves upon convex relaxation methods in a specific parameter regime; then, we demonstrate the application of our results for the optimization of particular two-dimensional, single-layer neural networks in realizable settings.

📄 PDF Abstract BibTeX arXiv:2204.07879

Code (1)

hadidaneshmand/measure_recovery_codes 공식 구현

Tasks

Super-ResolutionTensor Decomposition

Similar Papers 제목 키워드 기반

Recovery of binary sparse signals from compressed linear measurements via polynomial optimization

2019-05-30 · Sophie M. Fosson, Mohammad Abuabiah

The recovery of signals with finite-valued components from few linear measurements is a problem with widespread applications and interesting mathematical characteristics. In the compressed sensing framework, tailored met…

compressed sensing

Iterative Alpha Expansion for estimating gradient-sparse signals from linear measurements

2019-05-15 · Sheng Xu, Zhou Fan

We consider estimating a piecewise-constant image, or a gradient-sparse signal on a general graph, from noisy linear measurements. We propose and study an iterative algorithm to minimize a penalized least-squares objecti…

compressed sensing

Support Recovery in Universal One-bit Compressed Sensing

2021-07-19 · Arya Mazumdar, Soumyabrata Pal

One-bit compressed sensing (1bCS) is an extreme-quantized signal acquisition method that has been intermittently studied in the past decade. In 1bCS, linear samples of a high dimensional signal are quantized to only one …

compressed sensingQuantization

Improved Support Recovery in Universal One-bit Compressed Sensing

2022-10-29 · Namiko Matsumoto, Arya Mazumdar, Soumyabrata Pal

One-bit compressed sensing (1bCS) is an extremely quantized signal acquisition method that has been proposed and studied rigorously in the past decade. In 1bCS, linear samples of a high dimensional signal are quantized t…

compressed sensing

Hyperparameter Optimization in Neural Networks via Structured Sparse Recovery

2020-07-07 · Minsu Cho, Mohammadreza Soltani, Chinmay Hegde

In this paper, we study two important problems in the automated design of neural networks -- Hyper-parameter Optimization (HPO), and Neural Architecture Search (NAS) -- through the lens of sparse recovery methods. In the…

Hyperparameter OptimizationNeural Architecture Search