On computationally tractable selection of experiments in measurement-constrained regression models
From MaRDI portal
Publication:4637075
Abstract: We derive computationally tractable methods to select a small subset of experiment settings from a large pool of given design points. The primary focus is on linear regression models, while the technique extends to generalized linear models and Delta's method (estimating functions of linear regression models) as well. The algorithms are based on a continuous relaxation of an otherwise intractable combinatorial optimization problem, with sampling or greedy procedures as post-processing steps. Formal approximation guarantees are established for both algorithms, and numerical results on both synthetic and real-world data confirm the effectiveness of the proposed methods.
Recommendations
- A polynomial algorithm for best-subset selection problem
- Near-optimal discrete optimization for experimental design: a regret minimization approach
- Efficient computational algorithm for optimal continuous experimental designs
- Exact optimal experimental designs with constraints
- Study of a simple method and its consistency for selecting regression models in fixed and random designs
Cites work
- A statistical perspective on algorithmic leveraging
- A statistical perspective on randomized sketching for ordinary least-squares
- Budget feasible mechanisms for experimental design
- Constrained Adaptive Sensing
- Design for low-temperature microwave-assisted crystallization of ceramic thin films
- Design issues for generalized linear models: a review
- Faster least squares approximation
- Faster subset selection for matrices and applications
- Graph sparsification by effective resistances
- scientific article; zbMATH DE number 194139 (Why is no real title available?)
- scientific article; zbMATH DE number 1827860 (Why is no real title available?)
- scientific article; zbMATH DE number 800961 (Why is no real title available?)
- Interlacing families. I: Bipartite Ramanujan graphs of all degrees
- Interlacing families. II: Mixed characteristic polynomials and the Kadison-Singer problem
- Locally Optimal Designs for Estimating Parameters
- Matrix concentration inequalities via the method of exchangeable pairs
- On the rank of extreme matrices in semidefinite programs and the multiplicity of optimal eigenvalues
- Pipage rounding: a new method of constructing algorithms with proven performance guarantee
- Regularity properties for sparse regression
- Relative-Error CUR Matrix Decompositions
- Sampling from large matrices
- Semidefinite Programming
- Simultaneous analysis of Lasso and Dantzig selector
- Sketching as a tool for numerical linear algebra
- The Lasso problem and uniqueness
- Twice-Ramanujan sparsifiers
Cited in
(14)- A branch-and-bound algorithm for the exact optimal experimental design problem
- Near-optimal discrete optimization for experimental design: a regret minimization approach
- Orthogonal subsampling for big data linear regression
- Sketched ridge regression: optimization perspective, statistical perspective, and model averaging
- Gaussian process landmarking on manifolds
- Optimal Sampling for Generalized Linear Models Under Measurement Constraints
- LowCon: A Design-based Subsampling Approach in a Misspecified Linear Model
- A Local Search Framework for Experimental Design
- Model Checking in Large-Scale Dataset via Structure-Adaptive-Sampling
- A review on design inspired subsampling for big data
- Optimal Decorrelated Score Subsampling for High-Dimensional Generalized Linear Models Under Measurement Constraints
- Nonparametric Additive Models for Billion Observations
- Efficient Approximation of Leverage Scores in Two-Dimensional Autoregressive Models with Application to Image Anomaly Detection
- Balanced subsampling for big data with categorical predictors
This page was built for publication: On computationally tractable selection of experiments in measurement-constrained regression models
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q4637075)
