A unified approach to uniform signal recovery from nonlinear observations
DOI10.1007/s10208-022-09562-yarXiv2009.09185OpenAlexW3087634291MaRDI QIDQ6101267
Alexander Stollenwerk, Martin Genzel
Publication date: 20 June 2023
Published in: Foundations of Computational Mathematics (Search for Journal in Brave)
Full work available at URL: https://arxiv.org/abs/2009.09185
empirical processeshigh-dimensional estimationuniform recoverynonlinear observationsquantized compressed sensing
Ridge regression; shrinkage estimators (Lasso) (62J07) Parametric inference under constraints (62F30) Robustness and adaptive procedures (parametric inference) (62F35) Signal theory (characterization, reconstruction, filtering, etc.) (94A12)
Cites Work
- Unnamed Item
- Unnamed Item
- Nonlinear total variation based noise removal algorithms
- Upper bounds on product and multiplier empirical processes
- A mathematical introduction to compressive sensing
- The convex geometry of linear inverse problems
- Non-Gaussian hyperplane tessellations and robust one-bit compressed sensing
- Dimension reduction by random hyperplane tessellations
- One-bit compressed sensing with non-Gaussian measurements
- Reconstruction and subgaussian operators in asymptotic geometric analysis
- \(\ell^1\)-analysis minimization and generalized (co-)sparsity: when does recovery succeed?
- Learning without Concentration
- Convex Recovery of a Structured Signal from Independent Random Linear Measurements
- One-Bit Compressed Sensing by Linear Programming
- One-Bit Compressive Sensing With Norm Estimation
- The Generalized Lasso With Non-Linear Observations
- Robust 1-Bit Compressive Sensing via Binary Stable Embeddings of Sparse Vectors
- Robust 1-bit Compressed Sensing and Sparse Logistic Regression: A Convex Programming Approach
- Quantized Compressed Sensing: A Survey
- Quantization and Compressive Sensing
- On sparse reconstruction from Fourier and Gaussian measurements
- Robust uncertainty principles: exact signal reconstruction from highly incomplete frequency information
- Signal Parameter Estimation Using 1-Bit Dithered Quantization
- Dithered quantizers
- Fast and Reliable Parameter Estimation from Nonlinear Observations
- Guarantees of total variation minimization for signal recovery
- Time for dithering: fast and quantized random embeddings via the restricted isometry property
- High-dimensional estimation with geometric constraints: Table 1.
- Flavors of Compressive Sensing
- High-Dimensional Probability
- Structured Signal Recovery From Non-Linear and Heavy-Tailed Measurements
- Quantization
- Robust 1-bit compressed sensing via hinge loss minimization
- Quantized compressive sensing with RIP matrices: the benefit of dithering
- One-bit compressed sensing with partial Gaussian circulant matrices
- Compressed Sensing with 1D Total Variation: Breaking Sample Complexity Barriers via Non-Uniform Recovery
- Quickly Finding the Best Linear Model in High Dimensions via Projected Gradient Descent
- On Unlimited Sampling and Reconstruction
- The Generalized Lasso for Sub-Gaussian Measurements With Dithered Quantization
- Living on the edge: phase transitions in convex programs with random data
- Recovering Structured Data From Superimposed Non-Linear Measurements
- High-Dimensional Estimation of Structured Signals From Non-Linear Observations With General Convex Loss Functions
- Sharp Time–Data Tradeoffs for Linear Inverse Problems
- Upper and Lower Bounds for Stochastic Processes
- Stable signal recovery from incomplete and inaccurate measurements
- Phase Retrieval via Matrix Completion
- Compressed sensing
- Robust one-bit compressed sensing with partial circulant matrices
This page was built for publication: A unified approach to uniform signal recovery from nonlinear observations
