arXiv research

SL(n) covariant valuations on Orlicz spaces are represented and characterized.

Extends moment map concept to locally conformally Kähler manifolds.

Geometric approach to moment maps in complex geometry.

Investigates properties of moment maps and stratifications on Lie groups.

Study finds critical points of volume functionals on Sasaki manifolds.

The paper introduces a new method for tail bounds of random vectors and matrices.

The paper studies HKKN stratifications for non-compact spaces and proves convexity properties.

We show that if a compact Kaehler manifold $M$ of non-negative Ricci curvature admits closed Fedosov star product then the reduced Lie algebra of holomorphic vector fields on $M$ is reductive. This comes in pair with the obstruction previously found by La Fuente-Gravy. More generally we consider the squared norm of Cah…

We propose $β$-graph embedding for robustly learning feature vectors from data vectors and noisy link weights. A newly introduced empirical moment $β$-score reduces the influence of contamination and robustly measures the difference between the underlying correct expected weights of links and the specified generative m…

We introduce $Z$-critical connections for holomorphic vector bundles and prove their existence under stability conditions.

Proves conditions for weighted Hermite-Einstein metrics on vector bundles.

Two classification results for stationary surfaces of least moment of inertia.

Study geodesics in Kähler metrics for all time.

In this paper, we study the confounder detection problem in the linear model, where the target variable $Y$ is predicted using its $n$ potential causes $X_n=(x_1,...,x_n)^T$. Based on an assumption of rotation invariant generating process of the model, recent study shows that the spectral measure induced by the regress…

Improved GAN performance using higher-order Wasserstein moments.

We consider two stage estimation with a non-parametric first stage and a generalized method of moments second stage, in a simpler setting than (Chernozhukov et al. 2016). We give an alternative proof of the theorem given in (Chernozhukov et al. 2016) that orthogonal second stage moments, sample splitting and $n^{1/4}$-…

Deform moment map on symplectic connections using star product algebras.

The sequence of moments of a vector-valued random variable can characterize its law. We study the analogous problem for path-valued random variables, that is stochastic processes, by using so-called robust signature moments. This allows us to derive a metric of maximum mean discrepancy type for laws of stochastic proce…

Study local perturbations of vector bundles with polynomial curvature solutions.

New algorithm for batch list-decodable linear regression with stronger guarantees.

The paper derives risk measures for metalog distributions.

Deep learning representations of GAN data are like Gaussian mixtures, according to this study.

Study of generalized almost-Kähler-Ricci solitons and their implications.

Paper explores ML for UV spectra, showing transferability in chemical space.

We study the problem of estimating the mean of a random vector $X$ given a sample of $N$ independent, identically distributed points. We introduce a new estimator that achieves a purely sub-Gaussian performance under the only condition that the second moment of $X$ exists. The estimator is based on a novel concept of a…

We improve bounds for stochastic processes, especially those with heavy tails.

Independent component analysis (ICA) is the problem of efficiently recovering a matrix $A \in \mathbb{R}^{n\times n}$ from i.i.d. observations of $X=AS$ where $S \in \mathbb{R}^n$ is a random vector with mutually independent coordinates. This problem has been intensively studied, but all existing efficient algorithms w…

The space of symplectic connections on a symplectic manifold is a symplectic affine space. M. Cahen and S. Gutt showed that the action of the group of Hamiltonian diffeomorphisms on this space is Hamiltonian and calculated the moment map. This is analogous to, but distinct from, the action of Hamiltonian diffeomorphism…

We deal with the efficient parallelization of Bayesian global optimization algorithms, and more specifically of those based on the expected improvement criterion and its variants. A closed form formula relying on multivariate Gaussian cumulative distribution functions is established for a generalized version of the mul…

Consider a random vector with finite second moments. If its precision matrix is an M-matrix, then all partial correlations are non-negative. If that random vector is additionally Gaussian, the corresponding Markov random field (GMRF) is called attractive. We study estimation of M-matrices taking the role of inverse sec…

In the previous paper \cite{Goto_2017}, the notion of an Einstein-Hermitian metric of a generalized holomorphic vector bundle over a generalized Kahler manifold of symplectic type was introduced from the moment map framework. In this paper we establish a Kobayashi-Hitchin correspondence, that is, the equivalence of the…

Estimates mean of random vector with near-optimal error in all directions.

We compute higher moments of the Siegel--Veech transform over quotients of $SL(2,\mathbb{R})$ by the Hecke triangle groups. After fixing a normalization of the Haar measure on $SL(2,\mathbb{R})$ we use geometric results and linear algebra to create explicit integration formulas which give information about densities of…

Study of universal complexes in toric topology with applications in category theory.

The paper proposes a method to monitor deep learning predictions for retraining, reducing costs.

We describe a general framework -- compressive statistical learning -- for resource-efficient large-scale learning: the training collection is compressed in one pass into a low-dimensional sketch (a vector of random empirical generalized moments) that captures the information relevant to the considered learning task. A…

We prove that higher moment maps on area measures of a euclidean vector space are injective, while the kernel of the centroid map equals the image of the first variation map. Based on this, we introduce the space of smooth dual area measures on a finite-dimensional euclidean vector space and prove that it admits a natu…

Study resolvent convergence for random matrices with general covariance profiles.

Two examples of $\mathrm{Diff}^+S^1$-invariant closed two-forms obtained from forms on jet bundles, which does not admit equivariant moment maps are presented. The corresponding cohomological obstruction is computed and shown to coincide with a nontrivial Lie algebra cohomology class on $H^2(\mathfrak{X}(S^1))$.

Efficiently factorize tensors in streaming data with coreset selection.

New method uses geometric moments for accurate machine learning potentials.

The study proves the finiteness of moments for Gaussian field zeros and critical points.

We revisit the proof by Qin et al. (2014) of bounded regret of the C$^2$UCB contextual combinatorial bandit. We demonstrate an error in the proof of volumetric expansion of the moment matrix, used in upper bounding a function of context vector norms. We prove a relaxed inequality that yields the originally-stated regre…

We develop time-uniform confidence spheres for estimating means of random vectors.

Given a polarized complex manifold, projection of a torus-equivariant test configuration to holomorphic vector fields was introduced by G. Székelyhidi, as the limit of the associated $\mathbb{C}^*$-actions. We show that there actually holds the moment convergence of the weight distributions. Our analytic approach at th…

Iteratively reweighted least squares (IRLS) is a widely-used method in machine learning to estimate the parameters in the generalised linear models. In particular, IRLS for L1 minimisation under the linear model provides a closed-form solution in each step, which is a simple multiplication between the inverse of the we…

New methods for uncertainty in neural networks with leaky ReLU activations.

Let X(Σ) be a smooth projective toric variety for a complex torus T_\C. In this paper, a real T_\C-invariant Poisson structure Π_Σis constructed on the complex manifold X(Σ), the symplectic leaves of which are the T_\C-orbits in X(Σ). It is shown that each leaf admits a Hamiltonian action by a sub-torus of the compact …