Fast and Reliable Parameter Estimation from Nonlinear Observations

DOI10.1137/17M1113874zbMath1373.90120arXiv1610.07108OpenAlexW2964188360MaRDI QIDQ4588858

Mahdi Soltanolkotabi, Samet Oymak

Publication date: 3 November 2017

Published in: SIAM Journal on Optimization (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/1610.07108

zbMATH Keywords

quantizationsparsitynonlinear estimationprojected gradient descent

Mathematics Subject Classification ID

Analysis of algorithms and problem complexity (68Q25) Nonconvex programming, global optimization (90C26) Nonlinear ordinary differential equations and systems (34A34) Iterative numerical methods for linear systems (65F10) Randomized algorithms (68W20)

Related Items (4)

Generic error bounds for the generalized Lasso with sub-exponential data ⋮ Sharp global convergence guarantees for iterative nonconvex optimization with random data ⋮ A unified approach to uniform signal recovery from nonlinear observations ⋮ Solving inverse problems using data-driven models

Uses Software

• HOGWILD

Cites Work

• Unnamed Item
• Sharp MSE bounds for proximal denoising
• Decomposable norm minimization with proximal-gradient homotopy algorithm
• The restricted isometry property and its implications for compressed sensing
• A randomized Kaczmarz algorithm with exponential convergence
• The convex geometry of linear inverse problems
• One-bit compressed sensing with non-Gaussian measurements
• Exact matrix completion via convex optimization
• Estimation in High Dimensions: A Geometric Perspective
• A Proximal-Gradient Homotopy Method for the Sparse Least-Squares Problem
• From Denoising to Compressed Sensing
• The Generalized Lasso With Non-Linear Observations
• Robust 1-bit Compressed Sensing and Sparse Logistic Regression: A Convex Programming Approach
• Large-Scale Machine Learning with Stochastic Gradient Descent
• Robust uncertainty principles: exact signal reconstruction from highly incomplete frequency information
• Guaranteed Minimum-Rank Solutions of Linear Matrix Equations via Nuclear Norm Minimization
• High-dimensional estimation with geometric constraints: Table 1.
• Living on the edge: phase transitions in convex programs with random data
• Structured Signal Recovery From Quadratic Measurements: Breaking Sample Complexity Barriers via Nonconvex Optimization
• The LASSO Risk for Gaussian Matrices
• The Dynamics of Message Passing on Dense Graphs, with Applications to Compressed Sensing
• Corrupted Sensing: Novel Guarantees for Separating Structured Signals
• Sharp Time–Data Tradeoffs for Linear Inverse Problems
• Compressed sensing
• A unified framework for high-dimensional analysis of \(M\)-estimators with decomposable regularizers

This page was built for publication: Fast and Reliable Parameter Estimation from Nonlinear Observations