Study improves oracle inequality for tree graphs using total variation regularization.
problem Improving oracle inequality for tree graphs with total variation regularization.
method Generalized Fused Lasso result to tree graphs, using harmonic mean of distances.
result Proved a lower bound on compatibility constant for total variation penalty.
The paper derives oracle inequalities for estimators with fast and slow rates.
problem Developing fast and slow oracle inequalities for estimators.
method Direct study of analysis estimator and adaptation of Dalalyan, Hebiri and Lederer's arguments.
result Constant-friendly rates for (square root) total variation regularized estimators over graphs.
Total variation denoising improves image quality adaptively.
problem Improving image quality from noisy data.
method Total variation regularization for image denoising.
result Denoised images converge to true images at a parametric rate.
We focus on the maximum regularization parameter for anisotropic total-variation denoising. It corresponds to the minimum value of the regularization parameter above which the solution remains constant. While this value is well know for the Lasso, such a critical value has not been investigated in details for the total…
The paper develops a multi-kernel method with sparsity constraint for regression.
problem Developing a robust regression method with sparsity constraints.
method Banach-space formulation, generalized total-variation regularization, multi-kernel expansion, adaptive kernel positions, ℓ1 penalty on coefficients. result The method achieves sparsity in the kernel coefficients, reducing the number of active kernels to the number of data points.
The paper analyzes the statistical learnability of GAMs using TV regularization.
problem Statistical learnability of generalized additive models with TV regularization.
method Total variation (TV) as a complexity measure for functions in Lmc1(R)-space, and Rademacher complexity analysis. result Generalization error bounds for finite samples are derived, showing tight complexity in terms of m and p. New method for tensor completion using nonconvex dual total variation.
problem Tensor completion from partial measurements with exponential-family noise.
method Proposed dual-TV (DTV) regularizers for tensor completion under exponential-family noise.
result Theoretical upper bounds on recovery error for tensor completion.
Method estimates noise transition matrix from noisy labels without relying on unreliable class-posterior estimation.
problem Estimating noise transition matrix from noisy data.
method Total variation regularization to encourage distinguishable predicted probabilities.
result Consistent estimator of the noise transition matrix under mild assumptions.
Paper develops a new theory on Wasserstein DRO's variation regularization effect.
problem Developing a new theory for Wasserstein DRO's regularization effect.
method General theory on variation regularization effect of Wasserstein DRO.
result New generalization guarantees for adversarial robust learning.
The paper establishes prediction bounds for trend filtering with higher order total variation penalties.
problem Estimating signals with jumps of varying orders using total variation regularization.
method Combining oracle inequalities and interpolating vectors to bound effective sparsity.
result The ℓ1-penalty on (k−1)extth order differences allows adaptive estimation for k∈{1,2,3,4}. 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…
Hypergraphs allow one to encode higher-order relationships in data and are thus a very flexible modeling tool. Current learning methods are either based on approximations of the hypergraphs via graphs or on tensor methods which are only applicable under special conditions. In this paper, we present a new learning frame…
New method improves tensor completion by selectively preserving important elements.
problem Recovering corrupted high-dimensional tensor data with missing entries and noise.
method Tensor weighted correlated total variation (TWCTV) regularizer with ADMM algorithm.
result Superior performance in image completion, denoising, and background subtraction tasks.
New method for mesh denoising using TGV of normal vector field.
problem Improving mesh quality by removing noise.
method Proposes a novel TGV formulation for normal vector fields on triangular meshes.
result New method outperforms existing techniques in mesh denoising experiments.
This work improves texture segmentation by automatically tuning hyperparameters for Total-Variation.
problem The challenge is to automatically select hyperparameters for Total-Variation texture segmentation.
method The approach involves extending Stein's unbiased gradient estimator to handle correlated Gaussian noise, leading to an automatic tuning method.
result The method provides an automatic way to select hyperparameters for Total-Variation texture segmentation.
We present a convex approach to probabilistic segmentation and modeling of time series data. Our approach builds upon recent advances in multivariate total variation regularization, and seeks to learn a separate set of parameters for the distribution over the observations at each time point, but with an additional pena…
New geometric insights reveal properties of adversarial training problems.
problem Adversarial training in binary classification.
method Equivalence with regularized risk minimization and convex relaxations.
result Existence of minimal and maximal solutions, and regular solutions.
Paper introduces a new method to model epidemic dynamics with varying parameters.
problem Capturing discontinuous variations in epidemic model parameters.
method Total variation regularization with Iterated Nelder--Mead optimization.
result The method accurately models epidemic dynamics with instant changes.
Introduces HTV to measure function complexity in learning schemes.
problem Assessing the complexity of supervised-learning schemes.
method Defines Hessian-Schatten total variation (HTV) as a seminorm to quantify function complexity.
result HTV is invariant to rotations, scalings, and translations, and its minimum value is achieved for linear mappings.
Proposes a new model for image restoration combining deep learning and total variation.
problem Restoring images from limited data with low-rank constraints insufficient.
method Regularized Deep Matrix Factorized (RDMF) model using deep neural network's low-rank bias and total variation.
result Outperforms state-of-the-art models in image restoration from few observations.
Total variation and mean curvature flows on a Lie group quotient enhance and denoise crossing structures.
problem Preserving crossing curvilinear structures in image enhancement and denoising.
method Lifting images to the homogeneous space M=RdtimesSd−1, applying PDEs for TVF and MCF, and using locally optimal differential frames. result Better preservation of bundle boundaries and angular sharpness in fiber orientation densities at crossings compared to data-driven diffusions.
Unified regularization framework for visualizing CNNs.
problem Visualizing concepts learned by convolutional neural networks.
method Mathematical framework unifying regularization methods, Sobolev gradients.
result Sobolev filters provide sharper reconstructions and better control over scales.
In recent years, total variation (TV) and Euler's elastica (EE) have been successfully applied to image processing tasks such as denoising and inpainting. This paper investigates how to extend TV and EE to the supervised learning settings on high dimensional data. The supervised learning problem can be formulated as an…
Network Lasso classifies partially labeled data with high-dimensional features.
problem Classifying data points with limited labeled data and high-dimensional features.
method Logistic Network Lasso using total variation regularization and primal-dual splitting.
result Accurate classification achieved from limited labeled data via network structure.
The logistic network Lasso solves binary classification and clustering for network data.
problem Binary classification and clustering for network-structured data.
method Generalizes logistic regression to non-Euclidean network data, uses total variation regularization, and applies ADMM for scalability.
result Solves non-smooth convex regularized empirical risk minimization with logistic loss.
A new model corrects inhomogeneity in Optimal Transport with Boundary.
problem Inhomogeneity in UROT models for Optimal Transport with Boundary.
method Proposed a modified entropic regularization term to make UROT models homogeneous.
result Homogeneous UROT model preserves properties of standard UROT while correcting inhomogeneity.
This paper accelerates TV regularization algorithms by unrolling proximal gradient descent.
problem Solving Total Variation (TV) regularized problems with iterative algorithms.
method Unrolling proximal gradient descent solvers to learn their parameters.
result Two approaches to compute derivatives through proximal operators improve performance.
Regularized deep networks improve generalization and robustness.
problem Improving generalization and robustness of deep neural networks.
method Input gradient regularization combined with Lipschitz and adversarial robustness.
result Regularized models show improved adversarial robustness and generalization.
Estimates BV functions from noisy data using Voronoi diagrams.
problem Estimating multivariate BV functions from scattered noisy data.
method Form Voronoi diagram, solve optimization problem with discrete TV regularization.
result Voronoigram is minimax rate optimal for BV functions.
WCAT improves adversarial robustness on CIFAR-10.
problem Improving robustness against adversarial examples.
method Lipschitz regularization of the loss function.
result 11% improvement in adversarial robustness on CIFAR-10.
New method constructs Lefschetz fibrations with different regular fibers.
problem Constructing Lefschetz fibrations with varied regular fibers.
method Combinatorial extension of a simple construction method.
result Existence of PALFs with genus 1 regular fibers.
The paper develops estimators for variance in graph structures using fused lasso.
problem Variance estimation in graph-structured problems.
method Developed linear time estimator for homoscedastic case and total variation regularization estimator for heteroscedastic case.
result Minimax rates and consistency for variance estimation in various graph structures.
This paper studies least-square regression penalized with partly smooth convex regularizers. This class of functions is very large and versatile allowing to promote solutions conforming to some notion of low-complexity. Indeed, they force solutions of variational problems to belong to a low-dimensional manifold (the so…
Ideas from the image processing literature have recently motivated a new set of clustering algorithms that rely on the concept of total variation. While these algorithms perform well for bi-partitioning tasks, their recursive extensions yield unimpressive results for multiclass clustering tasks. This paper presents a g…
A new travel time tomography method uses adaptive dictionaries to model slowness variations.
problem Modeling and reconstructing slowness maps with varying scales and discontinuities.
method Local model (sparse patches) and global model (smooth constraints) integrated into a maximum a posteriori formulation.
result The LST approach effectively models both smooth and discontinuous slowness features.
The paper studies curves in Riemannian manifolds using total variation flow.
problem Analyzing the evolution of curves in Riemannian manifolds using total variation.
method Defining and proving the existence of strong solutions to the flow equations, showing variational equality, and proving convergence.
result Strong solutions converge to a constant map in finite time for non-positive sectional curvature.
Proposes a method to estimate discrete curvatures for image reconstruction.
problem Image reconstruction challenges due to non-convex, non-smooth, and highly non-linear first-order optimal conditions.
method Estimates discrete curvatures (mean and Gaussian) locally using differential geometry theory. Solves a weighted total variation minimization problem efficiently with ADMM.
result Demonstrates the effectiveness and superiority of the proposed variational models for various image reconstruction tasks.
Optimal pre-processing reduces disparate impact by minimizing total variation distance.
problem Achieving fairness in data outputs based on protected attributes.
method Using pre-processing to enforce fairness, minimizing total variation distance between pre-processed and original data distributions.
result The problem of fairness can be formulated as a linear program, efficiently solvable.
The paper connects neural collapse and low-rank bias in networks with L2 regularization.
problem Understanding the emergence of low-rank bias and neural collapse in L2-regularized networks.
method Unified theoretical framework linking TCV and rank of weight matrices, proving global optimality of DNC1, and establishing a benign landscape property.
result Zero TCV across intermediate layers minimizes representation cost under natural architectural constraints, and DNC1 is globally optimal.
Framework for designing nonlinearities in neural networks with slope constraints.
problem Designing nonlinearities with specific properties for signal processing.
method Variational framework with regularization for slope constraints and optimization of adaptive splines.
result Adaptive nonuniform linear splines achieve global optimum in constrained optimization.
Novel algorithm for separating moving camera video into static and dynamic components.
problem Foreground-background separation in noisy, moving camera video.
method Augmented robust PCA with total variation regularization, OptShrink low-rank matrix estimator.
result Panoramic low-rank component spanning entire field of view, automatically stitching corrupted data.
The paper improves SVM and localized SVM stability under triple perturbations.
problem Stability of SVMs and localized SVMs under triple perturbations.
method Generalizes and improves existing results, considering simultaneous variations in probability measure, regularization parameter, and kernel.
result Improved stability of SVMs and localized SVMs under triple perturbations.
We present an alternating augmented Lagrangian method for convex optimization problems where the cost function is the sum of two terms, one that is separable in the variable blocks, and a second that is separable in the difference between consecutive variable blocks. Examples of such problems include Fused Lasso estima…
We study additive models built with trend filtering, i.e., additive models whose components are each regularized by the (discrete) total variation of their kth (discrete) derivative, for a chosen integer k≥0. This results in kth degree piecewise polynomial components, (e.g., k=0 gives piecewise constant co…
This work provides guaranteed bounds on the total variation distance for univariate mixtures.
problem Lack of closed-form expressions for total variation distance between mixtures.
method Two methods: information monotonicity for lower bounds and geometric envelopes for upper bounds.
result Demonstrated tightness of bounds on Gaussian, Gamma, and Rayleigh mixtures.
We show a very simple and general total second variation formula for Perelman's W-functional at arbitrary points in the space of Riemannian metrics. Moreover we perform a study of the properties of the variations of Kähler structures. We deduce a quite simple and general total second variation formula for P…
Total variation minimization clusters partially labeled data points.
problem Clustering partially labeled data points in stochastic block models.
method Total variation minimization as a clustering method.
result Total variation minimization allows for accurate clustering under certain model parameters.
Flow matching KL divergence bound derived for smooth distributions.
problem Estimating smooth distributions efficiently.
method Deterministic upper bound on KL divergence derived from flow-matching loss.
result Flow matching achieves nearly minimax-optimal efficiency under TV distance.