arXiv research

New method relaxes TV distance for two-sample testing without distributional assumptions.

The paper examines how to test if two learning algorithms produce similar outcomes.

Paper proposes a method to estimate total variation distance for synthetic data fidelity.

Sharp inequality between TV and Hellinger distances for Gaussian mixtures.

Parallel sampling for smooth distributions with fast convergence.

Estimates TV distance between autoregressive models under different access models.

Study on kinetic Langevin diffusions and their couplings, showing subtle TV bounds and new non-Markovian couplings.

We analyze the performance of the Tukey median estimator under total variation (TV) distance corruptions. Previous results show that under Huber's additive corruption model, the breakdown point is 1/3 for high-dimensional halfspace-symmetric distributions. We show that under TV corruptions, the breakdown point reduces …

Flow matching KL divergence bound derived for smooth distributions.

New tester outperforms existing ones in uniformity testing.

Stable GFlowNets prevent loss spikes and mode collapse in training.

Paper studies statistical properties of DP data synthesis algorithms based on Bayesian networks.

Robustly clusters mixtures of Gaussians even with outliers.

Paper proposes a two-stage ranking for personalized TV recommendations.

Improved learning of multivariate Gaussians with imperfect advice.

The paper sets sample complexity bounds for learning high-dimensional simplices in noisy data.

We study \emph{TV regularization}, a widely used technique for eliciting structured sparsity. In particular, we propose efficient algorithms for computing prox-operators for $\ell_p$-norm TV. The most important among these is $\ell_1$-norm TV, for whose prox-operator we present a new geometric analysis which unveils a …

Langevin dynamics fails to produce accurate samples even with small score function errors.

Polynomial-time algorithm learns high-dimensional halfspaces without labels.

TVS-FNNs can approximate any continuous function on expanded input spaces.

New algorithm reduces TV-denoising to adaptive online learning.

Unified analysis of MPLE for Ising models with bounded operator norm or infinity norm.

This paper improves non-asymptotic bounds for denoising diffusions, focusing on the Ornstein-Uhlenbeck process.

Characterizing the phase transitions of convex optimizations in recovering structured signals or data is of central importance in compressed sensing, machine learning and statistics. The phase transitions of many convex optimization signal recovery methods such as $\ell_1$ minimization and nuclear norm minimization are…

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…

Principal component analysis (PCA) is an exploratory tool widely used in data analysis to uncover dominant patterns of variability within a population. Despite its ability to represent a data set in a low-dimensional space, the interpretability of PCA remains limited. However, in neuroimaging, it is essential to uncove…

Two new deterministic offspring selection methods reduce statistical distance in SMC and pMCMC.

Computer Vision and machine learning methods were previously used to reveal screen presence of genders in TV and movies. In this work, using head pose, gender detection, and skin color estimation techniques, we demonstrate that the gender disparity in TV in a South Asian country such as Bangladesh exhibits unique chara…

This paper accelerates TV regularization algorithms by unrolling proximal gradient descent.

New model for shape graph registration with partial matching constraints.

A new robust metric compares distributions more accurately than existing methods.

Decision trees and shallow neural networks have different geometric complexities, impacting their interpretability and accuracy.

We consider the problem of embedding unweighted, directed k-nearest neighbor graphs in low-dimensional Euclidean space. The k-nearest neighbors of each vertex provides ordinal information on the distances between points, but not the distances themselves. We use this ordinal information along with the low-dimensionality…

RFM uses tangent vector fields to match data on manifolds, analyzing TV convergence for Euler discretization.

RL helps optimize TVS fund composition for volatility control.

New algorithm samples from log-concave distributions with high accuracy in polynomial time.

New invariants derived from a modular category for links and 3-manifolds.

Improves diffusion models by controlling total variance and signal-to-noise-ratio.

Study sample complexity of robust binary hypothesis testing under different contamination models.

Optimal locally private hypothesis selection with interactive rounds.

New algorithms help machines forget old data efficiently.

A new RL framework allows removing user data without affecting performance.

Private density estimation in Wasserstein distance for geographic populations.

We analyze mixing times of three DA algorithms for regression models.

New framework robustly handles outliers in Wasserstein DRO for better decision-making.

Graphs with non-negative Ollivier-Ricci curvature cannot be expanders.

Diffusion models adapt to low-dimensional data regardless of coefficient choices.

TV-SurvCaus improves causal inference for dynamic treatments in survival analysis.