Difference-of-Convex Learning: Directional Stationarity, Optimality, and Sparsity
From MaRDI portal
Publication:5348469
DOI10.1137/16M1084754zbMath1369.90130OpenAlexW2743133559MaRDI QIDQ5348469
Miju Ahn, Jong-Shi Pang, Jack X. Xin
Publication date: 18 August 2017
Published in: SIAM Journal on Optimization (Search for Journal in Brave)
Full work available at URL: https://doi.org/10.1137/16m1084754
Nonconvex programming, global optimization (90C26) Numerical optimization and variational techniques (65K10) Statistical aspects of information-theoretic topics (62B10)
Related Items
Exact penalization for cardinality and rank-constrained optimization problems via partial regularization, An inexact successive quadratic approximation method for a class of difference-of-convex optimization problems, A truncated Newton algorithm for nonconvex sparse recovery, On two recent nonconvex penalties for regularization in machine learning, The DTC (difference of tangentially convex functions) programming: optimality conditions, Accelerated inexact composite gradient methods for nonconvex spectral optimization problems, Composite Difference-Max Programs for Modern Statistical Estimation Problems, Kurdyka-Łojasiewicz exponent via inf-projection, A unifying framework of high-dimensional sparse estimation with difference-of-convex (DC) regularizations, Difference-of-Convex Algorithms for a Class of Sparse Group $\ell_0$ Regularized Optimization Problems, Difference-of-Convex Learning: Directional Stationarity, Optimality, and Sparsity, Solving constrained nonsmooth group sparse optimization via group Capped-\(\ell_1\) relaxation and group smoothing proximal gradient algorithm, The subdifferential of measurable composite max integrands and smoothing approximation, Comparing solution paths of sparse quadratic minimization with a Stieltjes matrix, Structural properties of affine sparsity constraints, Computation of the maximum likelihood estimator in low-rank factor analysis, A successive difference-of-convex approximation method for a class of nonconvex nonsmooth optimization problems, Distributed nonconvex constrained optimization over time-varying digraphs, Sparse precision matrix estimation with missing observations, A proximal subgradient algorithm with extrapolation for structured nonconvex nonsmooth problems, A global two-stage algorithm for non-convex penalized high-dimensional linear regression problems, Proximal gradient method with extrapolation and line search for a class of non-convex and non-smooth problems, Hybrid Algorithms for Finding a D-Stationary Point of a Class of Structured Nonsmooth DC Minimization, Retraction-based first-order feasible methods for difference-of-convex programs with smooth inequality and simple geometric constraints, Linear-step solvability of some folded concave and singly-parametric sparse optimization problems, Error bound and isocost imply linear convergence of DCA-based algorithms to D-stationarity, Unnamed Item, Nonconvex optimization for robust tensor completion from grossly sparse observations, Unnamed Item, On the superiority of PGMs to PDCAs in nonsmooth nonconvex sparse regression, On the pervasiveness of difference-convexity in optimization and statistics, Decomposition Methods for Computing Directional Stationary Solutions of a Class of Nonsmooth Nonconvex Optimization Problems, A proximal difference-of-convex algorithm with extrapolation, DC programming and DCA: thirty years of developments, Minimization of transformed \(L_1\) penalty: theory, difference of convex function algorithm, and robust application in compressed sensing, Iteratively Reweighted Group Lasso Based on Log-Composite Regularization, Consistency bounds and support recovery of d-stationary solutions of sparse sample average approximations, On the Convergence to Stationary Points of Deterministic and Randomized Feasible Descent Directions Methods, Computation of second-order directional stationary points for group sparse optimization, Nonconvex and nonsmooth sparse optimization via adaptively iterative reweighted methods, Solving nonnegative sparsity-constrained optimization via DC quadratic-piecewise-linear approximations, Sparse Recovery via Partial Regularization: Models, Theory, and Algorithms, Estimation of Individualized Decision Rules Based on an Optimized Covariate-Dependent Equivalent of Random Outcomes, Nonmonotone Enhanced Proximal DC Algorithms for a Class of Structured Nonsmooth DC Programming, Unnamed Item, Group Sparse Optimization for Images Recovery Using Capped Folded Concave Functions, Robust Tensor Completion: Equivalent Surrogates, Error Bounds, and Algorithms, Penalty and Augmented Lagrangian Methods for Constrained DC Programming, Stochastic Difference-of-Convex-Functions Algorithms for Nonconvex Programming
Uses Software
Cites Work
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Coordinate descent algorithms for nonconvex penalized regression, with applications to biological feature selection
- Nearly unbiased variable selection under minimax concave penalty
- A unified approach to model selection and sparse recovery using regularized least squares
- The Adaptive Lasso and Its Oracle Properties
- DC approximation approaches for sparse optimization
- Point source super-resolution via non-convex \(L_1\) based methods
- A note on the complexity of \(L _{p }\) minimization
- Support recovery without incoherence: a case for nonconvex regularization
- Enhancing sparsity by reweighted \(\ell _{1}\) minimization
- Best subset selection, persistence in high-dimensional statistical learning and optimization under \(l_1\) constraint
- One-step sparse estimates in nonconcave penalized likelihood models
- Convex analysis approach to d. c. programming: Theory, algorithms and applications
- Exact penalty in d. c. programming
- DC formulations and algorithms for sparse optimization problems
- Minimization of transformed \(L_1\) penalty: theory, difference of convex function algorithm, and robust application in compressed sensing
- The DC (Difference of convex functions) programming and DCA revisited with DC models of real world nonconvex optimization problems
- Asymptotics for Lasso-type estimators.
- Least angle regression. (With discussion)
- Simultaneous analysis of Lasso and Dantzig selector
- Complexity of unconstrained \(L_2 - L_p\) minimization
- The Dantzig selector: statistical estimation when \(p\) is much larger than \(n\). (With discussions and rejoinder).
- Strong oracle optimality of folded concave penalized estimation
- Transactions on Computational Collective Intelligence XIII
- Computing B-Stationary Points of Nonsmooth DC Programs
- SparseNet: Coordinate Descent With Nonconvex Penalties
- Weighted Elastic Net Penalized Mean-Variance Portfolio Design and Computation
- Decoding by Linear Programming
- Near-Optimal Signal Recovery From Random Projections: Universal Encoding Strategies?
- Lectures on Stochastic Programming
- Superresolution via Sparsity Constraints
- Atomic Decomposition by Basis Pursuit
- Variable Selection via Nonconcave Penalized Likelihood and its Oracle Properties
- Local Strong Homogeneity of a Regularized Estimator
- Recovering Sparse Signals With a Certain Family of Nonconvex Penalties and DC Programming
- A Statistical View of Some Chemometrics Regression Tools
- Finite-Dimensional Variational Inequalities and Complementarity Problems
- Sparse Approximate Solutions to Linear Systems
- Likelihood-Based Selection and Sharp Parameter Estimation
- Iterative Solution of Nonlinear Equations in Several Variables
- Minimization of $\ell_{1-2}$ for Compressed Sensing
- Nonconcave Penalized Likelihood With NP-Dimensionality
- Regularization and Variable Selection Via the Elastic Net
- Difference-of-Convex Learning: Directional Stationarity, Optimality, and Sparsity
- Towards a Mathematical Theory of Super‐resolution
- Bregman Iterative Algorithms for $\ell_1$-Minimization with Applications to Compressed Sensing
- Optimally sparse representation in general (nonorthogonal) dictionaries via ℓ 1 minimization
- Pseudo-Convex Functions
- High Dimensional Thresholded Regression and Shrinkage Effect
- Compressed sensing