The Generalized Lasso With Non-Linear Observations
From MaRDI portal
Abstract: We study the problem of signal estimation from non-linear observations when the signal belongs to a low-dimensional set buried in a high-dimensional space. A rough heuristic often used in practice postulates that non-linear observations may be treated as noisy linear observations, and thus the signal may be estimated using the generalized Lasso. This is appealing because of the abundance of efficient, specialized solvers for this program. Just as noise may be diminished by projecting onto the lower dimensional space, the error from modeling non-linear observations with linear observations will be greatly reduced when using the signal structure in the reconstruction. We allow general signal structure, only assuming that the signal belongs to some set K in R^n. We consider the single-index model of non-linearity. Our theory allows the non-linearity to be discontinuous, not one-to-one and even unknown. We assume a random Gaussian model for the measurement matrix, but allow the rows to have an unknown covariance matrix. As special cases of our results, we recover near-optimal theory for noisy linear observations, and also give the first theoretical accuracy guarantee for 1-bit compressed sensing with unknown covariance matrix of the measurement vectors.
Cited in
(44)- Sparse sliced inverse regression via Lasso
- Linear regression with sparsely permuted data
- Optimal estimation of slope vector in high-dimensional linear transformation models
- Estimation from nonlinear observations via convex programming with application to bilinear regression
- High-dimensional index volatility models via Stein's identity
- Robust parameter estimation of regression models under weakened moment assumptions
- Optimal combination of linear and spectral estimators for generalized linear models
- The restricted isometry property of block diagonal matrices for group-sparse signal recovery
- Single-index composite quantile regression for ultra-high-dimensional data
- Convergence guarantee for the sparse monotone single index model
- Estimating covariance and precision matrices along subspaces
- A spin Glass model for reconstructing nonlinearly encrypted signals corrupted by noise
- Solving equations of random convex functions via anchored regression
- Localized Gaussian width of \(M\)-convex hulls with applications to Lasso and convex aggregation
- Fundamental limits of weak recovery with applications to phase retrieval
- Misspecified nonconvex statistical optimization for sparse phase retrieval
- Generic error bounds for the generalized Lasso with sub-exponential data
- An introduction to compressed sensing
- Fast and reliable parameter estimation from nonlinear observations
- Scalable approximations for generalized linear problems
- scientific article; zbMATH DE number 7370544 (Why is no real title available?)
- Ising model selection using ℓ 1-regularized linear regression: a statistical mechanics analysis*
- scientific article; zbMATH DE number 7306923 (Why is no real title available?)
- Variance-stabilization-based compressive inversion under Poisson or Poisson–Gaussian noise with analytical bounds
- High-dimensional varying index coefficient models via Stein's identity
- A simple tool for bounding the deviation of random matrices on geometric sets
- Generalised Rank Regression Estimator with Standard Error Adjusted Lasso
- Sharp global convergence guarantees for iterative nonconvex optimization with random data
- A theory of capacity and sparse neural encoding
- A unified approach to uniform signal recovery from nonlinear observations
- Robust inference for high‐dimensional single index models
- Just least squares: binary compressive sampling with low generative intrinsic dimension
- Understanding Implicit Regularization in Over-Parameterized Single Index Model
- On the determination of Lagrange multipliers for a weighted Lasso problem using geometric and convex analysis techniques
- Robust Signal Recovery for High-Dimensional Linear Log-Contrast Models with Compositional Covariates
- Uniform recovery guarantees for quantized corrupted sensing using structured or generative priors
- Isotonic regression meets Lasso
- Distributed semi-supervised single-index model with corruption
- Theoretical guarantees for low-rank compression of deep neural networks
- Robust decoding from binary measurements with cardinality constraint least squares
- Observable adjustments in single-index models for regularized M-estimators with bounded p/n
- Binary iterative hard thresholding converges with optimal number of measurements for 1-bit compressed sensing
- Functional linear and single-index models: a unified approach via Gaussian Stein identity
- Recovery performance of PhaseLift for phase retrieval from coded diffraction patterns
This page was built for publication: The Generalized Lasso With Non-Linear Observations
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2976986)
