Paper proposes equivalent Lipschitz surrogates for zero-norm and rank optimization problems.
problem Optimization problems involving zero-norm and rank functions.
method Reformulate as MPECs, use global exact penalty, eliminate dual variable to get surrogates.
result Obtained equivalent Lipschitz surrogates for zero-norm and rank optimization problems.
This work discovers algebraic structures from data using a differentiable measure.
problem Discovering discrete algebraic rules from data.
method Formalizes the problem through Cayley-table completion and uses HyperCube operator-valued tensor factorization.
result Derives an absolute lower bound for the differentiable measure of algebraic complexity, proving it is attained only for group structures.
Global minima found for multidimensional scaling with penalties.
problem Finding global minima in multidimensional scaling.
method Combining stress loss function with a quadratic penalty term to find minimizers.
result Trajectory of minimizers leads to global minima.
Unified framework guarantees exactness of asymmetric low-rank SDP learning.
problem Exactness of asymmetric low-rank SDP learning with a quadratic penalty.
method Unified regularized asymmetric Burer-Monteiro factorization framework.
result Explicit lower bound on penalty parameter γ for exactness. Paper develops exact convex optimization for neural networks with polynomial activations.
problem Training two-layer neural networks with nonlinear polynomial activations.
method Exact convex optimization using semidefinite programming.
result Global optimization of neural networks is polynomial-time computable.
Study neural architectures on learned latent graphs using Schrödinger dynamics.
problem Understanding neural architectures on learned latent graphs.
method Optimizes over stratified moduli space of weighted graphs with Kähler-Hessian metric.
result Multilayer stationary networks are equivalent to global stationary problems on supra-graphs.
The use of machine-learning in neuroimaging offers new perspectives in early diagnosis and prognosis of brain diseases. Although such multivariate methods can capture complex relationships in the data, traditional approaches provide irregular (l2 penalty) or scattered (l1 penalty) predictive pattern with a very limited…
Sparse optimization refers to an optimization problem involving the zero-norm in objective or constraints. In this paper, nonconvex approximation approaches for sparse optimization have been studied with a unifying point of view in DC (Difference of Convex functions) programming framework. Considering a common DC appro…
We consider a class of constrained optimization problems with a possibly nonconvex non-Lipschitz objective and a convex feasible set being the intersection of a polyhedron and a possibly degenerate ellipsoid. Such problems have a wide range of applications in data science, where the objective is used for inducing spars…
AutoShuffleNet learns permutation matrices in CNNs for improved accuracy.
problem Manual design of channel shuffling in ShuffleNet.
method Learning permutation matrices via an exact Lipschitz continuous penalty in deep learning.
result Improved classification accuracies on CIFAR-10 and ImageNet datasets.
Trimmed Lasso offers sparse modeling with robustness control.
problem Sparse modeling in linear regression with robustness.
method Trimmed Lasso penalty function and its analysis.
result Trimmed Lasso offers exact sparsity control and robustness.
New method solves constrained optimization problems efficiently.
problem Equality-constrained nonlinear, nonconvex optimization problems.
method Adaptive inexact Newton method with randomized iterative sketching.
result Global almost sure convergence and local linear/superlinear convergence.
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.
One-bit measurements widely exist in the real world, and they can be used to recover sparse signals. This task is known as the problem of learning halfspaces in learning theory and one-bit compressive sensing (1bit-CS) in signal processing. In this paper, we propose novel algorithms based on both convex and nonconvex s…
This paper proposes a new method for GLM estimation using distance penalties to handle constraints.
problem Handling constraints in generalized linear models (GLM) is complicated.
method The approach uses distance penalties to optimize the log-likelihood, avoiding shrinkage.
result Distance penalties provide a flexible and non-shrinking alternative to traditional penalties.
The paper improves risk bounds for maximum likelihood estimation with arbitrary penalties.
problem Improving risk bounds for maximum likelihood estimation with arbitrary penalties.
method Developed a more general inequality for arbitrary penalties, leading to exact risk bounds of order 1/n.
result Derived exact risk bounds of order 1/n for iid parametric models, improving on previous bounds.
Develops a local Fokker--Planck geometric framework for more accurate score estimation.
problem Inaccurate estimation of score function in non-linear, state-dependent drifts.
method Local Fokker--Planck geometric framework, time change to cumulative-variance coordinate, heat-ball mean-value representations, exact high-dimensional sampling.
result Exact local mean-value representations for the score and density, improved accuracy in low-density regions.
Paper calculates the exact error of LDA models.
problem Bayesian generalization error in Latent Dirichlet Allocation (LDA).
method Theoretical analysis of learning coefficient using algebraic geometry.
result Exact asymptotic form of LDA's generalization error.
Two important goals of high-dimensional modeling are prediction and variable selection. In this article, we consider regularization with combined L1 and concave penalties, and study the sampling properties of the global optimum of the suggested method in ultra-high dimensional settings. The L1-penalty provides th…
Proposes spred for solving L1 penalty with SGD.
problem Solving L1 penalty in optimization problems. method Reparametrization and SGD approach.
result Proves spred as an exact differentiable solver of L1. New algorithm tackles stochastic optimization with inequality constraints.
problem Stochastic optimization with inequality constraints in various applications.
method Active-set stochastic sequential quadratic programming (StoSQP) with a differentiable exact augmented Lagrangian.
result Global convergence for any initialization, KKT residuals converge to zero almost surely.
In this paper, we present a novel penalty approach for the numerical solution of continuously controlled HJB equations and HJB obstacle problems. Our results include estimates of the penalisation error for a class of penalty terms, and we show that variations of Newton's method can be used to obtain globally convergent…
A data filtering method for cluster analysis is proposed, based on minimizing a least squares function with a weighted ℓ0-norm penalty. To overcome the discontinuity of the objective function, smooth non-convex functions are employed to approximate the ℓ0-norm. The convergence of the global minimum points o…
New single-loop algorithm tackles weakly convex constraints in stochastic optimization.
problem Optimization with weakly convex constraints in machine learning.
method Single-loop penalty-based stochastic algorithm using hinge-based penalty.
result Achieves state-of-the-art complexity for finding approximate KKT solutions.
A new penalty-free method optimizes portfolios without quantum annealing penalties.
problem Optimizing portfolios with quantum annealing penalties.
method Removing the penalty term and using a classical feasibility projector.
result Significant reduction in chain-break fractions and post-processed regret.
Optimizes multi-period portfolios with tail-risk constraints using neural networks.
problem Maximizing expected return while managing tail-risk constraints over multiple periods.
method Recurrent neural network approach to approximate optimal policy.
result Validated in financial and insurance models, capturing long-term risk dynamics.
Unified framework for fair regression in aware and unaware settings.
problem Lack of principled methods for fair regression in unawareness settings.
method Formulated as an optimal transport problem, unifying aware and unaware settings.
result Characterizes optimal prediction functions via optimal transport maps under different penalties.
New method finds global Lagrangians for variational systems.
problem Constructing global variational principles for variational systems.
method Analyzing Lepage 2-forms and finding global Lagrangians for systems defined by homogeneous functions of degree \(c
eq 0, 1\).
result Locally variational systems defined by homogeneous functions of degree \(c
eq 0, 1\) are globally variational.
Paper analyzes SLOPE via AMP, providing an asymptotically sharp analysis and algorithmic approach.
problem Analyzing SLOPE's solution under Gaussian random designs.
method Developed an asymptotically exact characterization using approximate message passing.
result AMP iterates converge to the SLOPE solution in an asymptotic sense.
A geometric theory explains loss functions for robust representation learning.
problem Treats robustness, domain adaptation, and sensor drift as separate literatures.
method Estimates covariance Sigma_task and uses it to pin Jacobian penalties.
result Proves optimality and necessity of range coverage for penalty matrices.
In this article, we discuss various implementation of L1 filtering in order to detect some properties of noisy signals. This filter consists of using a L1 penalty condition in order to obtain the filtered signal composed by a set of straight trends or steps. This penalty condition, which determines the number of breaks…
HAMD optimizes cubic portfolios without quadratization, achieving better results.
problem Optimizing higher-order portfolio models with reduced distortion.
method Hybrid pipeline combining continuous Hamiltonian search, cardinality-preserving projection, and iterated local search.
result HAMD achieves significantly lower native cubic objective values than classical heuristics.
The paper studies how adding an ℓ2 penalty affects network embeddings.
problem The impact of ℓ2 regularization on network embeddings.
method Analyzes the asymptotic behavior of ℓ2 regularized node2vec embeddings under graphon theory.
result The learned embeddings asymptotically form a graphon with a nuclear-norm-type penalty.
When faced with a supervised learning problem, we hope to have rich enough data to build a model that predicts future instances well. However, in practice, problems can exhibit predictive heterogeneity: most instances might be relatively easy to predict, while others might be predictive outliers for which a model train…
Improved understanding of low-rank solutions in SDPs via smoothed analysis.
problem Finding low-rank solutions to semidefinite programs efficiently.
method Penalty function formulation and smoothed analysis to avoid worst-case matrices.
result All approximate local optima are global optima for rank-constrained SDPs under certain conditions.
Study uses deep learning for efficient hedging of long-term financial derivatives.
problem Optimizing hedging strategies for long-term financial derivatives with various penalties and stylized facts.
method Deep reinforcement learning applied to neural networks optimizing hedging policies with quadratic and non-quadratic penalties.
result Non-quadratic global hedging policies result in significantly smaller downside risk metrics and significant hedging gains.
The paper constructs Levi flat structures using structure sheaves and differential complexes.
problem Global solvability and regularity of Levi flat structures.
method Employing formal integrability and differential complexes, the paper constructs a resolution for the structure sheaf.
result Global exactness and Sobolev regularity of the differential complex for Levi flat structures.
Data-driven optimization improves mean-variance portfolios by penalizing norms.
problem Estimation error in mean-variance optimization.
method Augment MVO with norm penalties, use neural networks for optimization, and compute derivatives implicitly.
result Data-driven optimization reduces portfolio risk compared to standard MVO.
Study risk-sensitive market making with entropy regularization for better quote control.
problem Risk-sensitive market making with exponential utility and penalties.
method Entropy-regularized certainty-equivalent Bellman policies for discrete-time market dynamics.
result Proves convergence and performance bounds for entropy-regularized policies.
Paper addresses uncertainty in model generalization under regime shifts.
problem Uncertainty in model generalization under regime changes.
method Proposes a framework to quantify and separate regime mismatch and sensitivity.
result Obtains exact decomposition and minimax lower bound for regime-aware models.
AGS-CL selectively updates penalties based on node importance for continual learning.
problem Catastrophic forgetting in continual learning.
method Adaptive Group Sparsity (AGS) with proximal gradient descent.
result Significantly outperforms baselines on various continual learning benchmarks.
A new spline method for manifold learning using Hessian-based curvature penalties.
problem Learning manifolds with curvature penalties in high dimensions.
method Generalizes thin-plate splines to flat manifolds using Hessian matrices, minimizing square error with curvature constraints.
result Existence and uniqueness of the spline solution, expressed as Green's functions and Hessian approximations.
New algorithm tackles optimization with distributed constraints.
problem Optimization problems with generalized orthogonality constraints in a decentralized setting.
method Introduced a novel algorithm that tracks gradients and Jacobians simultaneously.
result Global convergence with an iteration complexity established.
New method simplifies classifier structure via topological complexity.
problem Global regularization in classifiers is structure agnostic.
method Topological regularization using persistent homology.
result Demonstrated effectiveness on various datasets.
We study global aspects of complete, non-singular asymptotically locally AdS spacetimes solving the vacuum Einstein equations whose conformal infinity is an arbitrary globally stationary spacetime. It is proved that any such solution which is asymptotically stationary to the past and future is itself globally stationar…
Unified analysis of neural networks in NPIV using 2SLS and MFLD.
problem Global convergence of neural networks in NPIV.
method Lifted perspective through MFLD, penalty gradient approach for bilevel optimization.
result First global convergence result of neural networks for 2SLS in NPIV.
Study analyzes sparse linear regression with SCAD penalty under noise, providing theoretical insights and practical tools.
problem Signal reconstruction in sparse linear regression with piecewise continuous nonconvex penalties.
method Theoretical analysis using replica method, development of cross-validation error formula, and annealing procedure.
result The SCAD estimator outperforms ℓ1 in a wide parameter range, with the global minimum of mean square error in the replica symmetric phase. 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…