Gradient estimation with simultaneous perturbation and compressive sensing
From MaRDI portal
Publication:4558484
zbMATH Open1471.62370arXiv1511.08768MaRDI QIDQ4558484FDOQ4558484
Authors: Vivek Borkar, Vikranth R. Dwaracherla, Neeraja Sahasrabudhe 
Publication date: 22 November 2018
Full work available at URL: https://arxiv.org/abs/1511.08768
Recommendations
- Multivariate stochastic approximation using a simultaneous perturbation gradient approximation
- Monte Carlo gradient estimation in high dimensions
- Optimal random perturbations for stochastic approximation using a simultaneous perturbation gradient approximation
- Adaptive stochastic approximation by the simultaneous perturbation method
- Compressive Hermite interpolation: sparse, high-dimensional approximation from gradient-augmented measurements
Learning and adaptive systems in artificial intelligence (68T05) Estimation in multivariate analysis (62H12) Stochastic approximation (62L20)
Cites Work
- Efficient global optimization of expensive black-box functions
- Near-Optimal Signal Recovery From Random Projections: Universal Encoding Strategies?
- Sliced Inverse Regression for Dimension Reduction
- Title not available (Why is that?)
- An Adaptive Estimation of Dimension Reduction Space
- Title not available (Why is that?)
- Stable signal recovery from incomplete and inaccurate measurements
- User-friendly tail bounds for sums of random matrices
- A mathematical introduction to compressive sensing
- The road to deterministic matrices with the restricted isometry property
- On the failure of concentration for the \(\ell_\infty\)-ball
- Multivariate stochastic approximation using a simultaneous perturbation gradient approximation
- Analysis \(\ell_1\)-recovery with frames and Gaussian measurements
- Nonconvergence to unstable points in urn models and stochastic approximations
- Fast Solution of $\ell _{1}$-Norm Minimization Problems When the Solution May Be Sparse
- Learning gradients on manifolds
- Survey of modeling and optimization strategies to solve high-dimensional design problems with computationally-expensive black-box functions
- A Dynamical System Approach to Stochastic Approximations
- Learning gradients: predictive models that infer geometry and statistical dependence
- Analysis and improvement of policy gradient estimation
- Do stochastic algorithms avoid traps?
- Asymptotic bias of stochastic gradient search
- Statistical optimization in high dimensions
- On the convergence, lock-in probability, and sample complexity of stochastic approximation
- A Noniterative Online Bayesian Algorithm for the Recovery of Temporally Correlated Sparse Vectors
Cited In (4)
- Spectral Compressed Sensing via Projected Gradient Descent
- A simple numerical method based simultaneous stochastic perturbation for estimation of high dimensional matrices
- Monte Carlo gradient estimation in high dimensions
- Compressive Hermite interpolation: sparse, high-dimensional approximation from gradient-augmented measurements
This page was built for publication: Gradient estimation with simultaneous perturbation and compressive sensing
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q4558484)
