arXiv research

A method refines weights to estimate smooth manifolds from noisy data.

New method controls false discoveries in real-time data streams.

Bayesian approach adapts deep network structure for continual learning.

Paper proposes SCQ and P-TAMS for structured OOD testing in high-stakes ML.

We construct a infinite-dimensional manifold structure adapted to analytic Lie pseudogroups of infinite type. More precisely, we prove that any isotropy subgroup of an analytic Lie pseudogroup of infinite type is a regular infinite-dimensional Lie group, modelled on a locally convex strict inductive limit of Banach spa…

In some previous papers, a Legendre duality between Lagrangian and Hamiltonian Mechanics has been developed. The (ρ,η)-tangent application of the Legendre bundle morphism associated to a Lagrangian L or Hamiltonian H is presented. Using that, a Legendre description of Lagrangian Mechanics and Hamiltonian Mechanics is d…

New methods using natural gradient for structured optimization.

Solvable structures, likewise solvable algebras of local symmetries, can be used to integrate scalar ODEs by quadratures. Solvable structures, however, are particularly suitable for the integration of ODEs with a lack of local symmetries. In fact, under regularity assumptions, any given ODE always admits solvable struc…

We study evolution of (strong Kähler with torsion) SKT structures via the pluriclosed flow on complex nilmanifolds, i.e. on compact quotients of simply connected nilpotent Lie groups by discrete subgroups endowed with an invariant complex structure. Adapting to our case the techniques introduced by Jorge Lauret for stu…

Banyaga has shown that the group of symplectomorphisms Symp(N) of a compact symplectic manifold (N,w) determines the symplectic structure. This motivates the study of the homotopy properties of Symp(N). Gromov has shown that the group of symplectomorphisms of N is homotopic to SO(3)\times SO(3) when N is the product of…

The Newman-Penrose-Perjes formalism is applied to smooth contact structures on riemannian 3-manifolds. In particular it is shown that a contact 3-manifold admits an adapted riemannian metric if and only if it admits a metric with a divergence-free, constantly twisting, geodesic congruence. The shear of this congruence …

New method improves speed of estimating bivariate functional data.

Develops Chern-Weil theory for singular foliations.

Optimal CATE estimation with structured contrast functions using KRR.

Spectral mixture (SM) kernels comprise a powerful class of generalized kernels for Gaussian processes (GPs) to describe complex patterns. This paper introduces model compression and time- and phase (TP) modulated dependency structures to the original (SM) kernel for improved generalization of GPs. Specifically, by adop…

Graph Convolutional Neural Networks (GCNNs) are generalizations of CNNs to graph-structured data, in which convolution is guided by the graph topology. In many cases where graphs are unavailable, existing methods manually construct graphs or learn task-driven adaptive graphs. In this paper, we propose Graph Learning Ne…

In this paper, we solve the problem of adapting classifiers across domains. We consider the problem of domain adaptation for multi-class classification where we are provided a labeled set of examples in a source dataset and we are provided a target dataset with no supervision. In this setting, we propose an adversarial…

The paper generalizes hyperkahler metrics near Lagrangian submanifolds.

ACVAEs improve on CVAEs by learning more flexible latent correlations.

Framework combines HMM and MTGCN for spatiotemporal causal inference in clinical data.

This study analyzes how cryptocurrency networks adapt to financial disruptions.

The paper studies hyperkähler structures and adapted complex structures using the Monge-Ampère equation.

Flexible algorithms for maximizing rewards in structured bandits.

Given a compact symplectic toric manifold $(M,ω, \mathbb{T})$, we identify a class $DGK_ω^{\mathbb{T}}(M)$ of $\mathbb{T}$-invariant generalized Kähler structures for which a generalisation the Abreu-Guillemin theory of toric Kähler metrics holds. Specifically, elements of $DGK_ω^{\mathbb{T}}(M)$ are characterized by t…

DIVI clusters noisy high-dimensional data with stable feature gating.

New origami structures adapt to over 100 shapes with minimal actuation.

Study on feature learning in Leaky ResNets, explaining bottleneck structure.

Reinforcement learning improves online matching by combining expert policies.

Study nonparametric covariance function estimation for noisy data.

Recent renewed interest in Sasakian manifolds is due mainly to the fact that they can provide examples of generalized Einstein manifolds, manifolds which are of great interest in mathematical models of various aspects of physical phenomena. Sasakian manifolds are odd dimensional counterparts of Kählerian manifolds to w…

A Markov Chain approach for aligning generative models from pairwise human preferences.