Study derives a limit functional for Willmore graphs with curvature penalization.
problem Optimizing Willmore graphs with curvature constraints.
method Interpreting penalization as Lagrange multiplier, deriving Γ-limit. result Derives a new limit functional for Willmore graphs.
In this paper, we establish the non-positivity of the second eigenvalue of the Schrödinger operator −div(Pr∇⋅)−Wr2 on a closed hypersurface Σn of Rn+1, where Wr is a power of the (r+1)-th mean curvature of Σn. In the case that this eigenvalue is null we have a…
Early training phase affects deep neural network optimization and generalization.
problem The choice of learning rate influences generalization in deep learning models.
method Showed that SGD implicitly penalizes the trace of the Fisher Information Matrix (FIM) from the start of training, and explicitly penalizing the trace of FIM improves generalization.
result Catastrophic Fisher explosion (large trace of FIM early in training) is linked to poor generalization.
Euler's elastica with monotone curvature is uniquely minimal.
problem Global minimality of planar elastica with monotone curvature.
method Proof of global minimality using clamped boundary conditions and length penalization.
result Every planar elastica with non-constant monotone curvature is uniquely minimal.
Study of mean curvature flow with obstacles using singular perturbation.
problem Obstacle problem associated to mean curvature flow.
method Geometric vanishing-viscosity approximation with singular perturbation.
result Generic level sets are distributional solutions of the obstacle problem.
Mirror flow in shallow neural networks shows similar implicit bias to gradient flow, with key differences in curvature penalties.
problem Analyzing implicit bias in shallow neural networks with mirror flow.
method Characterization through variational problems and scaled potentials.
result Mirror flow with scaled potentials induces a rich class of biases not captured by RKHS norms.
CD converges linearly for MCP/SCAD penalized least squares.
problem Recovering sparse signals from data.
method Coordinate descent for MCP/SCAD penalized least squares.
result CD converges linearly to solutions of MCP/SCAD penalized least squares.
Improved asset allocation strategies using penalized quantile regression.
problem Improving investment strategies in asset allocation.
method Post-penalization, nonconvex penalties, and optimal tuning parameter selection.
result Alternative methods outperform simple LASSO, especially for extreme risk.
Curvature penalties improve interpretability of KANs without sacrificing accuracy.
problem Pathologically high-curvature oscillations in KANs activations make them hard to interpret.
method Derived a curvature penalty and proved an upper bound on model curvature.
result KANs with curvature penalties achieve substantially smoother activations while maintaining accuracy.
Equivalence found between algorithmic regularization and convex penalization for convex losses.
problem Understanding the relationship between algorithmic regularization and convex penalization.
method Introducing a geometric condition and showing equivalence through optimization paths.
result Optimization paths of iterative algorithms on unregularized problems match those of corresponding penalized problems under certain conditions.
AgFlow speeds up model selection in penalized PCA.
problem Efficient model selection in penalized PCA for HDLSS settings.
method Implicit regularization effect of gradient flow to reduce computation complexity.
result AgFlow achieves the complete solution path of L2-penalized PCA.
Develops a method to predict stock returns with time-varying risk premia.
problem Predicting stock returns with time-varying risk premia while maintaining no-arbitrage restrictions.
method Penalized two-pass regression with time-varying factor loadings, incorporating penalization in the first pass and grouping in the second pass.
result The proposed method reduces prediction errors compared to other approaches.
Sparse-penalized deep neural networks improve performance in weakly dependent processes.
problem Nonparametric regression and classification under weak dependence.
method Sparse-penalized deep neural networks with oracle inequalities and convergence rates established.
result The proposed estimators outperform non-penalized ones in simulations.
Paper develops a new method for optimal stopping in American options.
problem Optimal stopping in American options with singular generators.
method Entropy-regularized penalization scheme for reflected BSDEs with singular generators.
result Limit of the penalization scheme solves a reflected BSDE with a logarithmically singular generator.
In high-dimensional data analysis, penalized likelihood estimators are shown to provide superior results in both variable selection and parameter estimation. A new algorithm, APPLE, is proposed for calculating the Approximate Path for Penalized Likelihood Estimators. Both the convex penalty (such as LASSO) and the nonc…
In this paper, we propose a one-pass algorithm on MapReduce for penalized linear regression \[f_λ(α, β) = \|Y - α\mathbf{1} - Xβ\|_2^2 + p_λ(β)\] where α is the intercept which can be omitted depending on application; β is the coefficients and pλ is the penalized function with penalizing parameter λ. $f_λ(α, β…
Study accelerates gradient methods in machine learning, revealing risk and stability connections.
problem Understanding the statistical risk of accelerated gradient methods in machine learning.
method Continuous-time analysis of Nesterov's accelerated gradient method and Polyak's heavy ball method for least squares regression.
result Connections between early stopping, stability, and curvature of loss function are revealed.
We consider a Canham-Helfrich-type variational problem defined over closed surfaces enclosing a fixed volume and having fixed surface area. The problem models the shape of multiphase biomembranes. It consists of minimizing the sum of the Canham-Helfrich energy, in which the bending rigidities and spontaneous curvatures…
New insights into balancing reward and fairness in stochastic MAB.
problem Balancing reward and fairness in stochastic multi-armed bandits.
method Formulated a penalization framework and proposed a hard-threshold UCB-like algorithm.
result Asymptotic fairness, nearly optimal regret, better reward-fairness tradeoff.
The MM algorithm improves robust penalized estimation for outlier-contaminated data.
problem Outliers in data affect the reliability of penalized estimation.
method Innovative MM algorithm for both convex and nonconvex loss functions.
result Established convergence theory for MM algorithm with various loss functions.
The paper classifies and analyzes the stability of elastic curves with fixed endpoints.
problem Classification and stability of pinned elasticae.
method Critical points of the length-penalized elastic bending energy among planar curves with fixed endpoints.
result Explicit parametrization and classification of all critical points with a threshold parameter \(\hatλ \simeq 0.70107\).
Unified framework for pattern recovery in penalized and thresholded estimation.
problem Pattern recovery in penalized and thresholded estimation methods.
method Defining a novel pattern notion based on subdifferentials, introducing accessibility and noiseless recovery conditions.
result Unified and extended conditions for pattern recovery in a broad class of penalized estimators.
New method improves feature selection in tree-based models.
problem Previous feature selection methods in tree-based models lack sufficient regularization and sub-optimal performance.
method Developed a new gain penalization approach for tree-based models that allows for flexible feature-specific importance weights.
result The new method improves out-of-sample performance, especially with correlated features.
In this paper, we study the performance of extremum estimators from the perspective of generalization ability (GA): the ability of a model to predict outcomes in new samples from the same population. By adapting the classical concentration inequalities, we derive upper bounds on the empirical out-of-sample prediction e…
Proposes a new robust expectile regression method for high-dimensional data.
problem Heterogeneity in high-dimensional data with heteroscedastic variance or inhomogeneous covariate effects.
method Iteratively reweighted ℓ1-penalization for robust expectile regression (retire).
result Oracle convergence rate after log(log d) iterations in high-dimensional settings.
In this paper we purpose a blockwise descent algorithm for group-penalized multiresponse regression. Using a quasi-newton framework we extend this to group-penalized multinomial regression. We give a publicly available implementation for these in R, and compare the speed of this algorithm to a competing algorithm --- w…
We prove a Gamma-convergence result for a family of bending energies defined on smooth surfaces in R3 equipped with a director field. The energies strongly penalize the deviation of the director from the surface unit normal and control the derivatives of the director. Such type of energies for example arise…
Study on elastic curves pinned at the boundary, focusing on minimizers and their interaction with obstacles.
problem Minimizing elastic bending energy for open planar curves with obstacles.
method Investigation of global minimizers and explicit solutions for different values of the penalization parameter.
result Explicit threshold for λ above which minimizers touch the obstacle, regardless of obstacle shape. Improved DPO framework penalizes preference uncertainty to avoid overoptimization.
problem Aligning LLMs to human preferences is challenging due to varied, context-dependent, and ambiguous preferences.
method Developed a pessimistic framework for DPO by introducing preference uncertainty penalization schemes.
result Improved overall performance and better completions on high-uncertainty responses compared to vanilla DPO.
New methods correct spectral distortions using known analyte concentrations.
problem Distorted spectral shapes from absorbing and scattering contributions.
method Modified penalized baseline correction methods that incorporate known analyte concentrations.
result Improved prediction performance on near infra-red data sets.
A new robust regression method handles outliers in high-dimensional data.
problem Outliers in high-dimensional data make conventional regression methods ineffective.
method Robust penalized least squares of depth trimmed residuals regression.
result The new method outperforms existing methods in estimation and prediction accuracy.
This paper introduces a gradient analysis framework to improve language model performance by rewarding good examples and penalizing bad ones.
problem Improving language model output quality by penalizing bad examples.
method Gradient analysis of loss functions to reward good examples and penalize bad ones.
result ExMATE is superior to MLE and combining DPO with ExMATE enhances performance.
Algorithm samples from Wasserstein barycenter of measures.
problem Sampling from Wasserstein barycenter of measures.
method Gradient flow of multimarginal formulation with penalization.
result Algorithm samples close to Wasserstein barycenter.
In many applications, multivariate samples may harbor previously unrecognized heterogeneity at the level of conditional independence or network structure. For example, in cancer biology, disease subtypes may differ with respect to subtype-specific interplay between molecular components. Then, both subtype discovery and…
A new Branch-and-Bound solver tackles L0-penalized problems with flexible loss functions.
problem Solving L0-penalized optimization problems with a broader class of loss functions.
method Generic Branch-and-Bound procedure with closed-form expressions for key quantities.
result El0ps solver achieves state-of-the-art performance and extends computational feasibility.
Develops a fast algorithm for high-dimensional LASSO penalized quantile regression.
problem Computational challenges in high-dimensional ℓ1 penalized quantile regression. method Pathwise coordinate descent algorithm to solve exact coordinatewise minimum of the nonsmooth loss function.
result Algorithm runs faster than existing alternatives and maintains estimation accuracy.
The paper tackles pricing vulnerable options via generalized BSDEs and penalization schemes.
problem Pricing options in a general hazard process setup.
method Establishes well-posedness and comparison theorems for generalized BSDEs and RBSDEs, studies penalization schemes.
result Well-posedness results and comparison theorems for generalized BSDEs and RBSDEs, extended penalization schemes.
XCAN uses cross-product penalization for sparse matrix factorization.
problem Understanding complex data structures.
method Sparse matrix factorization with a loss function balancing variance and structural preservation.
result Flexible modeling approach for diverse applications.
This paper optimizes portfolio selection by penalizing tracking error, improving Sharpe ratio.
problem Optimizing portfolio allocation with a penalty for deviation from a reference portfolio.
method Formulated as a McKean-Vlasov control problem, provides explicit solutions and asymptotic expansions.
result The penalized portfolio strategy outperforms standard mean-variance and reference portfolios in most cases.
Flexible empirical Bayes for large-scale multiple linear regression.
problem Large-scale multiple linear regression with flexible priors and efficient computation.
method Adaptive shrinkage priors combined with variational approximations for hyperparameter estimation.
result The posterior mean from the empirical Bayes method solves a penalized regression problem.
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.
L2-Boosting fails to recover sparse parameters in high-dimensional models.
problem Theoretical differences between L2-Boosting and L1-penalized methods like Lasso.
method Proof of theoretical property differences between L2-Boosting and L1-penalized methods.
result L2-Boosting does not guarantee parameter recovery in high-dimensional models.
Paper estimates differences in multi-attribute Gaussian graphical models using non-convex penalties.
problem Estimating differences in multi-attribute Gaussian graphical models with similar structure.
method Penalized D-trace loss function with non-convex (log-sum and SCAD) penalties, proximal gradient descent methods.
result Theoretical analysis and numerical examples support consistency in support recovery and estimation.
New method for evolving surfaces using generalized power mean curvature flow.
problem Evolve surfaces with volume penalization replaced by a generalized term.
method Generalized minimizing movement scheme converging to geometric evolution equation.
result Minimizing movements coincide with smooth classical solutions and preserve mean convexity.
We introduce a new probabilistic method for solving a class of impulse control problems based on their representations as Backward Stochastic Differential Equations (BSDEs for short) with constrained jumps. As an example, our method is used for pricing Swing options. We deal with the jump constraint by a penalization p…
We theoretically and empirically study portfolio optimization under transaction costs and establish a link between turnover penalization and covariance shrinkage with the penalization governed by transaction costs. We show how the ex ante incorporation of transaction costs shifts optimal portfolios towards regularized …
We propose a penalized orthogonal-components regression (POCRE) for large p small n data. Orthogonal components are sequentially constructed to maximize, upon standardization, their correlation to the response residuals. A new penalization framework, implemented via empirical Bayes thresholding, is presented to effecti…
Researchers develop a method to learn CTBN structure using penalized maximum likelihood.
problem Learning the structure of continuous-time Bayesian networks (CTBNs) when the dependence structure is unknown.
method Penalized maximum likelihood method.
result The algorithm can accurately identify the network structure with high probability under certain conditions.