A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.
Curvature penalties improve interpretability of KANs without sacrificing accuracy.
Unified analysis of multi-task functional linear regression with manifold and composite penalties.
Study dual representations for quasiconvex systemic risk measures.
Consider the stochastic composition optimization problem where the objective is a composition of two expected-value functions. We propose a new stochastic first-order method, namely the accelerated stochastic compositional proximal gradient (ASC-PG) method, which updates based on queries to the sampling oracle using tw…
We provide novel theoretical results regarding local optima of regularized -estimators, allowing for nonconvexity in both loss and penalty functions. Under restricted strong convexity on the loss and suitable regularity conditions on the penalty, we prove that \emph{any stationary point} of the composite objective f…
The stochastic gradient descent has been widely used for solving composite optimization problems in big data analyses. Many algorithms and convergence properties have been developed. The composite functions were convex primarily and gradually nonconvex composite functions have been adopted to obtain more desirable prop…
Develops consistent approximations for composite optimization problems.
New single-loop algorithm tackles weakly convex constraints in stochastic optimization.
We consider a group of mean-variance investors with mimicking desire such that each investor is willing to penalize deviations of his portfolio composition from compositions of other group members. Penalizing norm constraints are already applied for statistical improvement of Markowitz portfolio procedure in order to c…
In this paper we develop proximal methods for statistical learning. Proximal point algorithms are useful in statistics and machine learning for obtaining optimization solutions for composite functions. Our approach exploits closed-form solutions of proximal operators and envelope representations based on the Moreau, Fo…
We consider the stochastic nested composition optimization problem where the objective is a composition of two expected-value functions. We proposed the stochastic ADMM to solve this complicated objective. In order to find an stationary point where the expected norm of the subgradient of corresponding augmented Lag…
We study a hybrid conditional gradient - smoothing algorithm (HCGS) for solving composite convex optimization problems which contain several terms over a bounded set. Examples of these include regularization problems with several norms as penalties and a norm constraint. HCGS extends conditional gradient methods to cas…
The paper explores MMPR to select diverse models for scientific insight.
BacHMMachine harmonizes Baroque chorales using theory-driven principles and Hidden Markov Models.
Tree-AMP simplifies inference in complex tree-structured models.
Paper addresses uncertainty in model generalization under regime shifts.
Alternating direction method of multipliers (ADMM) is a popular optimization tool for the composite and constrained problems in machine learning. However, in many machine learning problems such as black-box attacks and bandit feedback, ADMM could fail because the explicit gradients of these problems are difficult or in…
Regularization methods are often employed in deep learning neural networks (DNNs) to prevent overfitting. For penalty based DNN regularization methods, convex penalties are typically considered because of their optimization guarantees. Recent theoretical work have shown that nonconvex penalties that satisfy certain reg…
We consider the problem of minimizing the sum of a smooth function with a bounded Hessian, and a nonsmooth function. We assume that the latter function is a composition of a proper closed function and a surjective linear map , with the proximal mappings of , , simple to compute. This problem i…
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…
The paper studies robust risk measures with linear penalties under uncertain distributions.
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…
New sparse penalty improves biclustering for gene expression data.
New approach avoids excess empirical risk in domain generalization.
We study the problem of estimating high-dimensional regression models regularized by a structured sparsity-inducing penalty that encodes prior structural information on either the input or output variables. We consider two widely adopted types of penalties of this kind as motivating examples: (1) the general overlappin…
A popular heuristic for improved performance in Generative adversarial networks (GANs) is to use some form of gradient penalty on the discriminator. This gradient penalty was originally motivated by a Wasserstein distance formulation. However, the use of gradient penalty in other GAN formulations is not well motivated.…
New method reduces bias in sparse Bayesian learning.
We consider a one-period Kyle (1985) framework where the insider can be subject to a penalty if she trades. We establish existence and uniqueness of equilibrium for virtually any penalty function when noise is uniform. In equilibrium, the demand of the insider and the price functions are in general non-linear and remai…
New nonconvex penalty smooths at origin for deep learning.
This work is an analytical and numerical study of the composition of several fractals into one and of the relation between the composite dimension and the dimensions of the component fractals. In the case of composition of standard IFS with segments of equal size, the composite dimension can be expressed as a function …
We study the problem of learning high dimensional regression models regularized by a structured-sparsity-inducing penalty that encodes prior structural information on either input or output sides. We consider two widely adopted types of such penalties as our motivating examples: 1) overlapping group lasso penalty, base…
Wasserstein GAN(WGAN) is a model that minimizes the Wasserstein distance between a data distribution and sample distribution. Recent studies have proposed stabilizing the training process for the WGAN and implementing the Lipschitz constraint. In this study, we prove the local stability of optimizing the simple gradien…
Multi-group learners suffer a penalty in transductive learning.
Global minima found for multidimensional scaling with penalties.
Paper addresses online alignment of large language models under uncertain preference feedback.
Proposes an alternative invariance penalty to address domain generalization issues.
Improved penalty-based methods for bilevel optimization with reduced complexity.
New geometric approach for analyzing compositional data like gut microbiomes.
Paper proposes efficient algorithms for designing SLOPE penalty sequences.
Insider trading is reduced when penalized, affecting expected penalties in a non-monotone way.
Study on deep neural networks using branching processes and Mehler's formula.
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…
Method solves nonconvex constrained optimization problems with a new augmented Lagrangian approach.
In high-dimensional and/or non-parametric regression problems, regularization (or penalization) is used to control model complexity and induce desired structure. Each penalty has a weight parameter that indicates how strongly the structure corresponding to that penalty should be enforced. Typically the parameters are c…
We establish conditions for compositional generalization in machine learning.
Improved online penalty selection for time series models.
In the multiple changepoint setting, various search methods have been proposed which involve optimising either a constrained or penalised cost function over possible numbers and locations of changepoints using dynamic programming. Such methods are typically computationally intensive. Recent work in the penalised optimi…
This paper proves hyperbolicity of virtual knot compositions.