arXiv research

This work compares regularization and constrained inference for label constraints in machine learning.

KL-constrained API shows optimization issues and improved with regularization.

The paper shows regularization can't always find all optimal solutions in constrained ML.

Koopman Regularization learns governing equations from sparse data.

Structured regularizers enable faster optimization on SPD manifolds with constraints.

Study minimizers of quasi-perimeters in RCD spaces with volume constraints.

DE-PSGLD samples from constrained distributions in a decentralized manner.

Symmetric TSP is structurally equivalent to a constrained Group Steiner Tree Problem.

This paper studies the regularity of constrained Willmore immersions into $\R^{m\ge3}$ locally around both "regular" points and around branch points, where the immersive nature of the map degenerates. We develop local asymptotic expansions for the immersion, its first, and its second derivatives, given in terms of resi…

This paper is concerned with the study of constrained statistical learning problems, the unconstrained version of which are at the core of virtually all of modern information processing. Accounting for constraints, however, is paramount to incorporate prior knowledge and impose desired structural and statistical proper…

Study Lipschitz regularity for manifold-constrained ROF model on curved surfaces.

Regularization aims to improve prediction performance of a given statistical modeling approach by moving to a second approach which achieves worse training error but is expected to have fewer degrees of freedom, i.e., better agreement between training and prediction error. We show here, however, that this expected beha…

AdamW optimizes a constrained loss with $\ell_\infty$ norm constraint.

This article reviews and explains HMC-based methods for sampling constrained continuous distributions.

A scalable framework optimizes multi-asset portfolios with constraints.

The $\ell_1$-norm fails to produce sparse solutions in Laplacian constrained graphical models, leading to a complete graph.

New method constrains CNN filter frequencies to improve robustness.

Unified framework for estimating high-dimensional conditional factor models.

This paper addresses the problem of sparsity penalized least squares for applications in sparse signal processing, e.g. sparse deconvolution. This paper aims to induce sparsity more strongly than L1 norm regularization, while avoiding non-convex optimization. For this purpose, this paper describes the design and use of…

Matrix completion has been well studied under the uniform sampling model and the trace-norm regularized methods perform well both theoretically and numerically in such a setting. However, the uniform sampling model is unrealistic for a range of applications and the standard trace-norm relaxation can behave very poorly …

Estimating the level set of a signal from measurements is a task that arises in a variety of fields, including medical imaging, astronomy, and digital elevation mapping. Motivated by scenarios where accurate and complete measurements of the signal may not available, we examine here a simple procedure for estimating the…

The paper tackles sampling from Gibbs measures with constrained support, providing a sampling guarantee.

We develop a 2D travel time tomography method which regularizes the inversion by modeling groups of slowness pixels from discrete slowness maps, called patches, as sparse linear combinations of atoms from a dictionary. We propose to use dictionary learning during the inversion to adapt dictionaries to specific slowness…

Let $(M,g)$ be a 3-dimensional Riemannian manifold. The goal of the paper it to show that if $P_{0}\in M$ is a non-degenerate critical point of the scalar curvature, then a neighborhood of $P_{0}$ is foliated by area-constrained Willmore spheres. Such a foliation is unique among foliations by area-constrained Willmore …

The concepts of risk-aversion, chance-constrained optimization, and robust optimization have developed significantly over the last decade. Statistical learning community has also witnessed a rapid theoretical and applied growth by relying on these concepts. A modeling framework, called distributionally robust optimizat…

Improves adversarial robustness by constraining logits with a bounded function.

Lockout solves sparse regularization for neural networks.

Choquet regularization improves exploration in RL.

Transfer learning through fine-tuning a pre-trained neural network with an extremely large dataset, such as ImageNet, can significantly accelerate training while the accuracy is frequently bottlenecked by the limited dataset size of the new target task. To solve the problem, some regularization methods, constraining th…

Extends Langevin dynamics for constrained domains.

Method solves nonconvex constrained optimization problems with a new augmented Lagrangian approach.

A novel Bayesian optimization framework tackles multi-objective constrained problems.

New method improves generative modeling on convex domains using regularized mirror maps and Student-t priors.

A new method constrains PARAFAC2 for better pattern recovery.

A new modal autoencoder improves feature extraction by constraining the decoder.

Generative AI connects to Schrödinger bridge problems with soft constraints for stability.

We formulate a principle for classification with the knowledge of the marginal distribution over the data points (unlabeled data). The principle is cast in terms of Tikhonov style regularization where the regularization penalty articulates the way in which the marginal density should constrain otherwise unrestricted co…

Enhances SSL with mixup and Lipschitz regularization.

Over the past few years, trace regression models have received considerable attention in the context of matrix completion, quantum state tomography, and compressed sensing. Estimation of the underlying matrix from regularization-based approaches promoting low-rankedness, notably nuclear norm regularization, have enjoye…

Consider a physical system for which a mathematically rigorous geometric quantization procedure exists. Now subject the system to a finite set of irreducible first class (bosonic) constraints. It is shown that there is a mathematically rigorous BRST quantization of the constrained system whose cohomology at ghost numbe…

RSAC improves lightweight continuous learning efficiency.

This paper presents a geometric description on Lie algebroids of Lagrangian systems subject to nonholonomic constraints. The Lie algebroid framework provides a natural generalization of classical tangent bundle geometry. We define the notion of nonholonomically constrained system, and characterize regularity conditions…

New method uses constrained transport metric for robust Bayesian inference.

Optimal bounds on regret and constraint violation in adversarial COCO.

We consider a singular control problem with regime switching that arises in problems of optimal investment decisions of cash-constrained firms. The value function is proved to be the unique viscosity solution of the associated Hamilton-Jacobi-Bellman equation. Moreover, we give regularity properties of the value functi…

Sponsored search in E-commerce platforms such as Amazon, Taobao and Tmall provides sellers an effective way to reach potential buyers with most relevant purpose. In this paper, we study the auction mechanism optimization problem in sponsored search on Alibaba's mobile E-commerce platform. Besides generating revenue, we…

The paper tackles safe reinforcement learning with convex regularization.

Rapidly growing product lines and services require a finer-granularity forecast that considers geographic locales. However the open question remains, how to assess the quality of a spatio-temporal forecast? In this manuscript we introduce a metric to evaluate spatio-temporal forecasts. This metric is based on an Opti- …