Complete Dictionary Recovery Over the Sphere I: Overview and the Geometric Picture
From MaRDI portal
Publication:2989630
DOI10.1109/TIT.2016.2632162zbMath1364.94164arXiv1511.03607OpenAlexW2601846890MaRDI QIDQ2989630
No author found.
Publication date: 8 June 2017
Published in: IEEE Transactions on Information Theory (Search for Journal in Brave)
Full work available at URL: https://arxiv.org/abs/1511.03607
Related Items (max. 100)
Analysis of Asymptotic Escape of Strict Saddle Sets in Manifold Optimization ⋮ Optimization landscape of Tucker decomposition ⋮ Global Convergence of Stochastic Gradient Hamiltonian Monte Carlo for Nonconvex Stochastic Optimization: Nonasymptotic Performance Bounds and Momentum-Based Acceleration ⋮ Unnamed Item ⋮ Unnamed Item ⋮ Unnamed Item ⋮ Unnamed Item ⋮ Solving orthogonal group synchronization via convex and low-rank optimization: tightness and landscape analysis ⋮ Likelihood landscape and maximum likelihood estimation for the discrete orbit recovery model ⋮ Unnamed Item ⋮ Implicit regularization in nonconvex statistical estimation: gradient descent converges linearly for phase retrieval, matrix completion, and blind deconvolution ⋮ An envelope for Davis-Yin splitting and strict saddle-point avoidance ⋮ Decentralized nonconvex optimization with guaranteed privacy and accuracy ⋮ Adaptive trust-region method on Riemannian manifold ⋮ First-order methods almost always avoid strict saddle points ⋮ Nearly optimal bounds for the global geometric landscape of phase retrieval ⋮ A Trust Region Method for Finding Second-Order Stationarity in Linearly Constrained Nonconvex Optimization ⋮ A Newton-Based Method for Nonconvex Optimization with Fast Evasion of Saddle Points ⋮ Rayleigh quotient minimization for absolutely one-homogeneous functionals ⋮ Median-Truncated Gradient Descent: A Robust and Scalable Nonconvex Approach for Signal Estimation ⋮ Applied harmonic analysis and data processing. Abstracts from the workshop held March 25--31, 2018 ⋮ Exact Recovery of Multichannel Sparse Blind Deconvolution via Gradient Descent ⋮ Unnamed Item ⋮ Learning semidefinite regularizers ⋮ The global optimization geometry of shallow linear neural networks ⋮ A convex variational model for learning convolutional image atoms from incomplete data ⋮ Finding a low-rank basis in a matrix subspace ⋮ Unnamed Item ⋮ Unnamed Item ⋮ Spectral Compressed Sensing via Projected Gradient Descent ⋮ On Collaborative Compressive Sensing Systems: The Framework, Design, and Algorithm ⋮ Proximal Gradient Method for Nonsmooth Optimization over the Stiefel Manifold ⋮ ADMM for multiaffine constrained optimization ⋮ Sensor calibration for off-the-grid spectral estimation ⋮ Compressed dictionary learning ⋮ On the Landscape of Synchronization Networks: A Perspective from Nonconvex Optimization ⋮ Unnamed Item ⋮ Quadratic optimization with orthogonality constraint: explicit Łojasiewicz exponent and linear convergence of retraction-based line-search and stochastic variance-reduced gradient methods ⋮ Weakly Convex Optimization over Stiefel Manifold Using Riemannian Subgradient-Type Methods ⋮ On the geometric analysis of a quartic-quadratic optimization problem under a spherical constraint ⋮ The Global Landscape of Phase Retrieval II: Perturbed Amplitude Models ⋮ The Global Landscape of Phase Retrieval II: Quotient Intensity Models ⋮ One-dimensional system arising in stochastic gradient descent ⋮ An active-set proximal quasi-Newton algorithm for ℓ1-regularized minimization over a sphere constraint ⋮ Identifiability of Complete Dictionary Learning ⋮ Extending the Step-Size Restriction for Gradient Descent to Avoid Strict Saddle Points ⋮ Data clustering based on the modified relaxation Cheeger cut model ⋮ Solving phase retrieval with random initial guess is nearly as good as by spectral initialization
This page was built for publication: Complete Dictionary Recovery Over the Sphere I: Overview and the Geometric Picture
