arXiv research

A new Wasserstein distance method for comparing incomparable distributions.

This thesis tackles Optimal Transport on incomparable spaces, proposing new tools and properties.

Generative Adversarial Networks have shown remarkable success in learning a distribution that faithfully recovers a reference distribution in its entirety. However, in some cases, we may want to only learn some aspects (e.g., cluster or manifold structure), while modifying others (e.g., style, orientation or dimension)…

Proposes GDTW for aligning time series on different, incomparable spaces.

The paper constructs wild Cantor sets in high dimensions.

Framework benchmarks optimizers on multiple criteria.

Local surrogate explainers vary in objectives, leading to incomparable explanations.

A new algorithmic framework is proposed for learning autoencoders of data distributions. We minimize the discrepancy between the model and target distributions, with a \emph{relational regularization} on the learnable latent prior. This regularization penalizes the fused Gromov-Wasserstein (FGW) distance between the la…

We propose an SDP relaxation for the Gromov-Wasserstein distance, providing globally optimal solutions.

Two commonly arising computational tasks in Bayesian learning are Optimization (Maximum A Posteriori estimation) and Sampling (from the posterior distribution). In the convex case these two problems are efficiently reducible to each other. Recent work (Ma et al. 2019) shows that in the non-convex case, sampling can som…

Researchers analyze neural process architectures and their representational capacities.

Faster GW alignment for incomparable point clouds via low-rank couplings.

Unbalanced COOT improves feature alignment robustly to outliers.

A new method for federated learning aggregates data from multiple sites efficiently.

PolyGraph Discrepancy improves graph generative model evaluation.

The PARAFAC2 is a multimodal factor analysis model suitable for analyzing multi-way data when one of the modes has incomparable observation units, for example because of differences in signal sampling or batch sizes. A fully probabilistic treatment of the PARAFAC2 is desirable in order to improve robustness to noise an…

The paper addresses calibration in label ranking, a structured prediction task.

This paper benchmarks speech LVMs against deterministic models and adapts a video model to speech.

Robotic grasp stability improved with fingertip slippage detection.

In this work, we initiate a formal study of probably approximately correct (PAC) learning under evasion attacks, where the adversary's goal is to \emph{misclassify} the adversarially perturbed sample point $\widetilde{x}$, i.e., $h(\widetilde{x})\neq c(\widetilde{x})$, where $c$ is the ground truth concept and $h$ is t…

This work shows how evaluation metrics can be seen as fair gambles.

New method detects Kaehler scalar flat metrics and minimal hypersurfaces.

Paper explores learning patterns in binary sequences, finding no method consistently outperforms others.

GD outperforms ridge regression and SGD in linear regression problems.

Proposes an efficient lower bound for Gromov-Wasserstein discrepancy.

Hierarchical Partial-Order Models for Ranking

Feature selection, in the context of machine learning, is the process of separating the highly predictive feature from those that might be irrelevant or redundant. Information theory has been recognized as a useful concept for this task, as the prediction power stems from the correlation, i.e., the mutual information, …

Unified platform SOCRATES for neural network analysis.

Online Streaming Feature Selection (OSFS) is a sequential learning problem where individual features across all samples are made available to algorithms in a streaming fashion. In this work, firstly, we assert that OSFS's main assumption of having data from all the samples available at runtime is unrealistic and introd…

This paper solves optimal consumption-investment problems with time-varying preferences.

NATS-Bench benchmarks NAS algorithms for architecture topology and size.

Quantum algorithm estimates multivariate mean with near-optimal efficiency.

New design method improves Lasso performance in sparse regression.

The paper explores solutions to the distributional Bellman equation in reinforcement learning.

Proposes vMF distribution for skewed elliptical distributions.

Study calculates tail risk for various mixture distributions.

We realise the first and second Grushin distributions as symmetry reductions of the 3-dimensional Heisenberg distribution and 4-dimensional Engel distribution respectively. Similarly, we realise the Martinet distribution as an alternative symmetry reduction of the Engel distribution. These reductions allow us to derive…

Recent work has shown that deep generative models assign higher likelihood to out-of-distribution inputs than to training data. We show that a factor underlying this phenomenon is a mismatch between the nature of the prior distribution and that of the data distribution, a problem found in widely used deep generative mo…

Method uses optimal transport to complete distributional matrices.

Income and wealth distribution affect stability of a society to a large extent and high inequality affects it negatively. Moreover, in the case of developed countries, recently has been proven that inequality is closely related to all negative phenomena affecting society. So far, Econophysics papers tried to analyse in…

Study clusters distributions with known or unknown clusters using distribution testing.

Gradually Truncated Log-normal distribution - Size distribution of firms Abstract Many natural and economical phenomena are described through power law or log- normal distributions. In these cases, probability decreases very slowly with step size compared to normal distribution. Thus it is essential to cut-off these di…

A new distribution family extends the $\alpha$-stable distribution with a degree of freedom parameter.

Paper develops a new method to improve model calibration under distribution shifts.

New class of heavy-tailed distributions shows weighted averages dominate individual variables.

Researchers derived formulas for joint moments of elliptical distributions.

Paper proposes a new method for designing materials using deep learning.

One-shot algorithm for feature-distributed kernel PCA reduces communication costs.