arXiv research

Self-affine arcs without inner weak separation are parabolic segments.

New graph types help identify complex relationships.

Study Poincaré inequality in metric spaces via separating sets.

The paper examines subgroup separability for surface and virtual braid groups.

New framework for cyclic quantum causal models with graph separation property.

Categorical d-separation criterion simplifies probability graph analysis.

Develops large-sample theory for non-stationary source separation.

New concept of regular separation for ODEs leads to improved Hardy field results.

Reservoir computing's success depends on mapping different input time series to separable states.

We present a separation property for the gaps in the length spectrum of a compact Riemannian manifold with negative curvature. In arbitrary small neighborhoods of the metric for some suitable topology, we show that there are negatively curved metrics with a length spectrum exponentially separated from below. This prope…

This paper provides a mathematical framework for time-delay reservoir computing.

We prove that the separated curve complex of a closed orientable surface of genus g is (g-3)-connected. We also obtain a connectivity property for a separated curve complex of the open surface that is obtained by removing a finite set from a closed one, but it is then assumed that the removed set is endowed with a part…

Paper develops robust methods for panel data with latent groups, improving inference under group separation violations.

Adversarial noises are linearly separable for random neural networks.

The complement of a non-separating planar graph contains a K_n minor.

Logistic regression is one of the most popular methods in binary classification, wherein estimation of model parameters is carried out by solving the maximum likelihood (ML) optimization problem, and the ML estimator is defined to be the optimal solution of this problem. It is well known that the ML estimator exists wh…

We solve the equivalence problem for the orthogonally separable webs on the three-sphere under the action of the isometry group. This continues a classical project initiated by Olevsky in which he solved the corresponding canonical forms problem. The solution to the equivalence problem together with the results by Olev…

Method separates target signal properties from noisy mixtures.

PeL separates sensory interface optimization from decision learning.

Gradient descent converges with arbitrary stepsize for separable data under Fenchel-Young losses.

A new measure DCSI quantifies separability for density-based clustering.

New complex connects graph separability to group properties.

The separability assumption (Donoho & Stodden, 2003; Arora et al., 2012) turns non-negative matrix factorization (NMF) into a tractable problem. Recently, a new class of provably-correct NMF algorithms have emerged under this assumption. In this paper, we reformulate the separable NMF problem as that of finding the ext…

Confocal quadrics lie at the heart of the system of confocal coordinates (also called elliptic coordinates, after Jacobi). We suggest a discretization which respects two crucial properties of confocal coordinates: separability and all two-dimensional coordinate subnets being isothermic surfaces (that is, allowing a con…

We focus on emergence of the power-law cross-correlations from processes with both short and long term memory properties. In the case of correlated error-terms, the power-law decay of the cross-correlation function comes automatically with the characteristics of separate processes. Bivariate Hurst exponent is then equa…

We extend a recently proposed 1-nearest-neighbor based multiclass learning algorithm and prove that our modification is universally strongly Bayes-consistent in all metric spaces admitting any such learner, making it an "optimistically universal" Bayes-consistent learner. This is the first learning algorithm known to e…

Proves conditions for separating regions in homogeneous spaces without trivial topology.

We show linear XOR classification is possible and propose equality separation for anomaly detection.

Let $\mathcal M (Σ, \mathcal P)$ be the mapping class group of a punctured oriented surface $(Σ, \mathcal P)$ (where $\mathcal P$ may be empty), and let $\mathcal T_p(Σ,\mathcal P)$ be the kernel of the action of $\mathcal M (Σ, \mathcal P)$ on $H_1 (Σ\setminus \mathcal P, \mathbb F_p)$. We prove that $\mathcal T_p(Σ, …

Shallow nonlinear networks can separate classes linearly with polynomially scaling width.

We classify pro-$p$ Poincaré duality pairs in dimension two. We then use this classification to build a pro-$p$ analogue of the curve complex and establish its basic properties. We conclude with some statements concerning separability properties of the mapping class group.

The paper connects decision tree interpretability and robustness through separation.

Generalizes underlap coefficient for multivariate group separation.

The paper defines Fenchel conjugate and biconjugate on Hadamard manifolds.

Hierarchical clustering is a popular method for analyzing data which associates a tree to a dataset. Hartigan consistency has been used extensively as a framework to analyze such clustering algorithms from a statistical point of view. Still, as we show in the paper, a tree which is Hartigan consistent with a given dens…

Non-negative matrix factorization (NMF) is a natural model of admixture and is widely used in science and engineering. A plethora of algorithms have been developed to tackle NMF, but due to the non-convex nature of the problem, there is little guarantee on how well these methods work. Recently a surge of research have …

This work presents a novel approach to train invertible linear layers by adding rank-one perturbations.

We answer a question of Aschenbrenner and Friedl regarding virtual $p$-efficiency for 3-manifold groups. We then study conjugacy $p$-separability and prove results for Fuchsian groups, Seifert fibre spaces and graph manifolds.

The paper studies conditions for exact posterior modeling in Bayesian networks.

Nonnegative matrix factorization (NMF) is a linear dimensionality technique for nonnegative data with applications such as image analysis, text mining, audio source separation and hyperspectral unmixing. Given a data matrix $M$ and a factorization rank $r$, NMF looks for a nonnegative matrix $W$ with $r$ columns and a …

Develops a new framework for causal models on cyclic graphs, solving unique solvability issues.

Thirty years after the birth of foliations in the 1950's, André Haefliger has introduced a special property satisfied by holonomy pseudogroups of foliations on compact manifolds, called compact generation. Up to now, this is the only general property known about holonomy on compact manifolds. In this article, we give a…

We propose $\ell_1$ norm regularized quadratic surface support vector machine models for binary classification in supervised learning. We establish their desired theoretical properties, including the existence and uniqueness of the optimal solution, reduction to the standard SVMs over (almost) linearly separable data s…

We propose a novel computational strategy for de novo design of molecules with desired properties termed ReLeaSE (Reinforcement Learning for Structural Evolution). Based on deep and reinforcement learning approaches, ReLeaSE integrates two deep neural networks - generative and predictive - that are trained separately b…

New non-separable covariance kernels for spatiotemporal data derived from harmonic oscillator physics.

We show that two properly embedded self-shrinkers in Euclidean space that are sufficiently separated at infinity must intersect at a finite point. The proof is based on a localized version of the Reilly formula applied to a suitable f-harmonic function with controlled gradient. In the immersed case, a new direct proof …

For all but finitely many compact orientable surfaces, we show that any superinjective map from the complex of separating curves into itself is induced by an element of the extended mapping class group. We apply this result to proving that any finite index subgroup of the Johnson kernel is co-Hopfian. Analogous propert…

A new NMF model for co-clustering and data approximation.