The article studies a combined L1 and concave regularization method for high-dimensional models.
problem Tackles variable selection and prediction in high-dimensional settings.
method Uses combined L1 and concave penalties to optimize model sparsity and prediction risk. result Global optimum of the method achieves oracle prediction risk and false sign rate bounds.
In this paper we will provide a representation of the penalty term of general dynamic concave utilities (hence of dynamic convex risk measures) by applying the theory of g-expectations.
Two new methods improve block-sparse signal recovery from noisy data.
problem Recovering block-sparse signals with unknown partitions.
method LogLOP-l2/l1 and AdaLOP-l2/l1 methods using log-sum penalty and MCP.
result Our methods outperform existing techniques in estimation accuracy.
New method approximates sampling from smooth potential distributions using a vanishing penalty.
problem Sampling from smooth potential distributions on high-dimensional spaces.
method Penalized Langevin dynamics (PLD) with vanishing penalty.
result Established upper bound on Wasserstein-2 distance for PLD approximation.
In this paper we study nonconvex penalization using Bernstein functions. Since the Bernstein function is concave and nonsmooth at the origin, it can induce a class of nonconvex functions for high-dimensional sparse estimation problems. We derive a threshold function based on the Bernstein penalty and give its mathemati…
As surrogate functions of L0-norm, many nonconvex penalty functions have been proposed to enhance the sparse vector recovery. It is easy to extend these nonconvex penalty functions on singular values of a matrix to enhance low-rank matrix recovery. However, different from convex optimization, solving the nonconvex l…
Sparse reconstruction approaches using the re-weighted l1-penalty have been shown, both empirically and theoretically, to provide a significant improvement in recovering sparse signals in comparison to the l1-relaxation. However, numerical optimization of such penalties involves solving problems with l1-norms in the ob…
Efficient ADMM algorithm solves nonconvex SVMs with various penalties.
problem Solving nonconvex penalized SVMs due to nondifferentiability, nonsmoothness, and nonconvexity.
method ADMM-based algorithm for a wide range of nonconvex penalties.
result The proposed algorithm outperforms other methods on benchmark datasets.
Variable selection is a fundamental task in statistical data analysis. Sparsity-inducing regularization methods are a popular class of methods that simultaneously perform variable selection and model estimation. The central problem is a quadratic optimization problem with an l0-norm penalty. Exactly enforcing the l0-no…
New method recovers signals from saturated data using linear loss and nonconvex penalties.
problem Signal recovery from saturated measurements with sign information loss.
method Linear loss and nonconvex penalties (e.g., minimax concave penalty, sorted ℓ1 norm).
result Estimation error is bounded and recovery performance improved.
Paper proposes algorithms for robust 1-bit compressive sensing with nonconvex penalties.
problem Recovering sparse signals from one-bit measurements.
method Develops algorithms based on convex and nonconvex penalties, providing analytical solutions.
result Analytical solutions for several nonconvex penalties are found, making the recovery process faster and more efficient.
New method improves signal reconstruction with nonconvex penalties and parameter control.
problem Reconstructing sparse signals with nonconvex penalties and nonconvexity control.
method Introduces nonconvex penalties (SCAD, MCP) with nonconvexity parameters and controls them to guide AMP trajectory.
result Achieves perfect reconstruction for relatively dense signals with small nonconvexity parameters.
In this paper we propose and study a family of sparsity-inducing penalty functions. Since the penalty functions are related to the kinetic energy in special relativity, we call them \emph{kinetic energy plus} (KEP) functions. We construct the KEP function by using the concave conjugate of a χ2-distance function and …
In sparse Bayesian learning (SBL), Gaussian scale mixtures (GSMs) have been used to model sparsity-inducing priors that realize a class of concave penalty functions for the regression task in real-valued signal models. Motivated by the relative scarcity of formal tools for SBL in complex-valued models, this paper propo…
Improved Frank-Wolfe algorithm solves saddle point problems efficiently.
problem Solving constrained smooth convex-concave saddle point problems.
method Extends Frank-Wolfe algorithm to use linear minimization oracles.
result First proof of convergence for FW-type saddle point solver over polytopes.
A new algorithm speeds up sparse-penalized quantile regression solving non-convex penalties.
problem Sparse-penalized quantile regression with non-convex penalties.
method Single-loop smoothing ADMM (SIAD) algorithm for faster convergence.
result SIAD method outperforms existing approaches in solving sparse-penalized quantile regression.
This paper uses concave conjugacy theory to analyze self-paced learning.
problem Understanding the intrinsic mechanism of self-paced learning.
method Proposes a concave conjugacy theory to analyze self-paced learning.
result Proves the equivalence of SPL regime and a latent concave objective.
Develops a statistical learning framework for personalized asset allocation.
problem Continuous-action decision-making with a large number of characteristics.
method Discretization approach with generalized penalties for penalized regression.
result Improves financial well-being with individualized optimal asset allocation.
Paper characterizes regularization methods' asymptotic equivalence in high-dimensional data.
problem Debate on which regularization method dominates in high-dimensional data.
method Characterizes asymptotic equivalence of convex and concave regularization methods.
result Concave methods are asymptotically equivalent to L1-regularization (Lasso) for polynomially growing dimensionality.
Proposes new ℓ0-based methods for low-rank sparse subspace clustering.
problem Clustering high-dimensional data points represented by low-dimensional subspaces.
method Introduces two ℓ0 quasi-norm based regularizations: GMC-LRSSC and S0/ℓ0-LRSSC. Solves resulting nonconvex optimization problems using alternating direction method of multipliers. result Demonstrates effectiveness of proposed methods on synthetic and real-world datasets.
Estimating mean from one-bit samples of symmetric log-concave distributions.
problem Estimating the mean of a symmetric log-concave distribution with limited one-bit measurements.
method Analyzes mean squared error in three settings: centralized, adaptive, and distributed, with and without quantization.
result One round of adaptivity is sufficient to achieve optimal mean-square error in the adaptive setting.
Paper optimizes DC pension fund management with VaR and relative performance constraints.
problem Optimizing DC pension fund performance under VaR and relative performance constraints.
method Introduced an auxiliary process to transform the problem into a self-financing problem, combined linearization, Lagrange dual, martingale, and concavification methods.
result Explicit investment strategies obtained for certain penalty and reward functions.
Fast accumulation of large amounts of complex data has created a need for more sophisticated statistical methodologies to discover interesting patterns and better extract information from these data. The large scale of the data often results in challenging high-dimensional estimation problems where only a minority of t…
SCOPE fuses categorical variable levels to estimate high-dimensional linear models.
problem Estimating high-dimensional linear models with nominal categorical data.
method SCOPE uses nonconvex concave penalties to fuse levels and achieve efficient computation.
result SCOPE achieves oracle least squares solution under certain conditions.
Proposes a neural network framework for feature selection in high-dimensional settings.
problem Challenges in feature selection and non-linear function estimation in high-dimensional settings.
method Sparse-input neural networks using group concave regularization.
result Establishes finite-sample guarantees for variable selection consistency and prediction accuracy.
New convex relaxations solve sparse regression problems efficiently.
problem Sparse regression with ℓ0 constraint is NP-hard. method Rank-one convexification for semidefinite optimization.
result Stronger and more general convex relaxations for sparse regression.
High throughput genetic sequencing arrays with thousands of measurements per sample and a great amount of related censored clinical data have increased demanding need for better measurement specific model selection. In this paper we establish strong oracle properties of nonconcave penalized methods for nonpolynomial (N…
New method improves tensor completion and robust PCA using non-convex tensor rank and sparsity measures.
problem Challenging tensor rank minimization in machine learning.
method Proposes a non-convex tensor rank surrogate function and sparsity measure, using concavity for optimization.
result Demonstrates improved accuracy and efficiency in tensor completion and robust PCA.
Proposes a new algorithm for online decision-making with high-dimensional data.
problem Online decision-making with high-dimensional data.
method G-MCP-Bandit algorithm with 2-step weighted Lasso procedure.
result Achieves optimal cumulative regret and convergence rate.
Unified framework connects two market-making models, revealing their underlying equivalence.
problem Independent calibration of two market-making frameworks (Avellaneda-Stoikov and Cartea-Jaimungal).
method Axiomatic approach to market preference functional, showing equivalence under specific conditions.
result Avellaneda-Stoikov and Cartea-Jaimungal frameworks are equivalent under certain conditions.
In this paper, we consider the problem of recovering a sparse signal based on penalized least squares formulations. We develop a novel algorithm of primal-dual active set type for a class of nonconvex sparsity-promoting penalties, including ℓ0, bridge, smoothly clipped absolute deviation, capped ℓ1 and mini…
We develop a penalized likelihood estimation framework to estimate the structure of Gaussian Bayesian networks from observational data. In contrast to recent methods which accelerate the learning problem by restricting the search space, our main contribution is a fast algorithm for score-based structure learning which …
Concave elliptic operators yield concave functions on cohomology.
problem Understanding concave functions on cohomology.
method General construction of concave elliptic operators.
result Generalized Khovanskii-Teissier inequalities.
A new method lifts training of input-convex neural networks to avoid dead weights and plateaued loss.
problem Training input-convex neural networks with non-negative weights.
method Introduces a hypernetwork that emits non-negative weights from a summary of the input batch, adding stochasticity to soften the loss landscape.
result The lift method achieves lower test loss than projected gradient descent and direct softplus reparametrization.
The paper establishes conditions for strict power concavity in convolutions.
problem Conditions for strict power concavity in convolutions.
method Analyzes sufficient conditions for strict parabolic power concavity of convolutions.
result Establishes sufficient conditions for strict power concavity of convolutions.
Minimal graph level sets are concave if boundary is concave.
problem Understanding curvature of minimal graph level sets.
method Proved an inequality and showed geometric properties.
result Level sets of minimal graphs are concave if boundary is concave.
Simple connection between Harnack inequalities and concavity of arrival time functions.
problem Proving differential Harnack inequalities for various flows.
method Directly proving concavity properties of time-of-arrival functions for a class of flows using a concavity maximum principle.
result Short proof of Hamilton's and Andrews' differential Harnack inequalities.
Proves log-concavity of cluster algebra coefficients for type An.
problem Log-concavity of cluster algebra coefficients.
method Introduced atomic theta basis and proved log-concavity for type An. result Proved log-concavity of coefficients for cluster algebra variables of type An. Study improves sampling from non-log-concave distributions using Fisher information.
problem Sampling from non-log-concave distributions with high Fisher information guarantees.
method Proximal sampler with RGO implementation, leveraging log-concave sampling results.
result Improved complexity guarantee in relative Fisher information for non-log-concave sampling.
Established concavity principle for curved spaces.
problem Solving equations on curved spaces with nonnegative curvature.
method Applied concavity principle to elliptic and parabolic equations on locally symmetric spaces with nonnegative curvature.
result First general concavity principle on spaces with non-constant sectional curvature.
Trans-Ising combines auxiliary datasets to estimate high-dimensional Ising models.
problem Limited target sample sizes and difficulty in using auxiliary binary datasets of unknown relevance.
method Trans-Ising uses a loss-based source screening rule and a two-stage estimation procedure.
result Trans-Ising achieves lower estimation errors than target-only estimation and naive data pooling.
Establishes log-concavity estimates for convex domains' first Dirichlet eigenfunctions.
problem Quantifying the Hessian of log-concave eigenfunctions on convex domains.
method Analyzes log-concavity properties of the first Dirichlet eigenfunction on convex domains.
result Obtains quantitative estimates for the Hessian of logu. New saddle network architectures preserve convex-concave geometry in optimization problems.
problem Optimization models with convex x and concave y components.
method Structured separable decomposition and saddle network architectures.
result Proven one-dimensional approximation theorem and high accuracy on various test functions.
This work improves information concentration for exp-concave distributions, making it dimension-independent.
problem Challenges in information concentration for log-concave distributions with dimension dependence.
method Proves exp-concavity leads to dimension-independent information concentration using a novel variance Brascamp-Lieb inequality.
result Information concentration depends only on the exp-concavity parameter, not the dimension.
Investigates concavity of spacetimes, showing conditions for local concavity.
problem Understanding the concavity of spacetimes in Finsler geometry.
method Analyzes flag curvature and future capsules to characterize concavity.
result Berwald spacetimes are locally concave if and only if their flag curvature is nonnegative in timelike directions.
Heat flow fails to preserve concavity in curved spaces.
problem Non-preservation of concavity properties in curved spaces.
method Analysis of Dirichlet heat flow on Riemannian manifolds.
result No concavity properties are preserved unless curvature is zero.
Log-concave densities characterized using peacock and zonoid concepts.
problem Characterizing log-concave densities.
method Characterization using peacock and zonoid concepts.
result Two characterizations of log-concave densities.
The paper calibrates robust optimization models to reduce sensitivity to model errors.
problem Reducing sensitivity of expected reward to model errors in empirical optimization.
method Develops a theory for data-driven calibration of robustness parameter δ using resampling methods.
result Substantial variance reduction is possible at little cost if δ is properly calibrated.