arXiv research

Nonnegative sectional curvature linked to matrix displacement convexity.

In this note we continue the analysis of metric measure space with variable ricci curvature bounds. First, we study $(κ,N)$-convex functions on metric spaces where $κ$ is a lower semi-continuous function, and gradient flow curves in the sense of a new evolution variational inequality that captures the information that …

The curvature-dimension condition is a generalization of the Bochner inequality to weighted Riemannian manifolds and general metric measure spaces. It is now known to be equivalent to evolution variational inequalities for the heat semigroup, and quadratic Wasserstein distance contraction properties at different times.…

Study measures inequality in social-economic systems using Fokker-Planck equations and Lotka-Volterra dynamics.

Theory of space-time currents for geometric evolutions.

Study of curve evolution in 2D space forms converging to a circle.

This is the first of a series of papers devoted to a thorough analysis of the class of gradient flows in a metric space $(X,\mathsf{d})$ that can be characterized by Evolution Variational Inequalities. We present new results concerning the structural properties of solutions to the $\mathrm{EVI}$ formulation, such as co…

Inspired by the work of Chen-Zhang \cite{Chen-Zhang}, we derive an evolution formula for the Wang-Yau quasi-local energy in reference to a static space, introduced by Chen-Wang-Wang-Yau \cite{CWWY}. If the reference static space represents a mass minimizing, static extension of the initial surface $Σ$, we observe that …

New method predicts state evolution for non-first-order algorithms on nonconvex problems.

The paper studies extremal hypersurfaces in ellipsoids using centro-affine geometry.

Neural networks solve variational inequalities for optimal stopping problems.

Global calculus for manifolds with boundary, solving evolution problems.

Approximate message passing (AMP) refers to a class of efficient algorithms for statistical estimation in high-dimensional problems such as compressed sensing and low-rank matrix estimation. This paper analyzes the performance of AMP in the regime where the problem dimension is large but finite. For concreteness, we co…

We prove local Poincaré inequalities under various curvature-dimension conditions which are stable under the measured Gromov-Hausdorff convergence. The first class of spaces we consider is that of weak CD(K,N) spaces as defined by Lott and Villani. The second class of spaces we study consists of spaces where we have a …

Evolving smooth, compact hypersurfaces in R^{n+1} with normal speed equal to a positive power k of the mean curvature improves a certain 'isoperimetric difference' for k >= n-1. As singularities may develop before the volume goes to zero, we develop a weak level-set formulation for such flows and show that the above mo…

The paper constructs a Dirichlet form and proves functional inequalities for a specific measure.

Study on slow convergence in geometric variational problems.

Sharp inequalities and eigenvalue problems on Finsler manifolds with nonnegative Ricci curvature.

The biharmonic flow and Willmore flow are studied in higher dimensions using geometric evolution equations.

Unified approach to analysis on Ricci nonnegative manifolds and flows using optimal transport.

New Harnack inequality for curve shortening flow without convexity.

We introduce variational approximations for curve evolutions in two-dimensional Riemannian manifolds that are conformally flat, i.e.\ conformally equivalent to the Euclidean space. Examples include the hyperbolic plane, the hyperbolic disk, the elliptic plane as well as any conformal parameterization of a two-dimension…

Algorithm improves variational inference in Wasserstein distance.

In this article and in its sequel we propose the study of certain discretizations of geometric evolution equations as an approach to the study of the existence problem of some elliptic partial differential equations of a geometric nature as well as a means to obtain interesting dynamics on certain infinite-dimensional …

Survey of methods for solving smooth stochastic variational inequalities.

We propose a family of variational approximations to Bayesian posterior distributions, called $α$-VB, with provable statistical guarantees. The standard variational approximation is a special case of $α$-VB with $α=1$. When $α\in(0,1]$, a novel class of variational inequalities are developed for linking the Bayes risk …

New methods reduce communication in distributed training for variational inequalities.

For a scalar evolution equation $u_t=K(t,x,u,u_x,\ldots, u_n), n\geq 2$ the cohomology spaces $H^{1,s}({\mathcal R}^\infty)$ vanishes for $s\geq 3$ while the space $H^{1,2}({\mathcal R}^\infty)$ is isomorphic to the space of variational operators. The cohomology space $H^{1,2}({\mathcal R}^\infty)$ is also shown to be …

NES optimizes discrete structured VAEs effectively without gradient propagation.

A variational inequality for pricing the perpetual American option and the corresponding difference equation are considered. First, the maximum principle and uniqueness of the solution to variational inequality for pricing the perpetual American option are proved. Then the maximum principle, the existence and uniquenes…

This paper combines three techniques to reduce communications in distributed variational inequalities.

We generalize the theory of gradient flows of semi-convex functions on CAT(0)-spaces, developed by Mayer and Ambrosio--Gigli--Savaré, to CAT(1)-spaces. The key tool is the so-called "commutativity" representing a Riemannian nature of the space, and all results hold true also for metric spaces satisfying the commutativi…

The geometry of a Lagrangian mechanical system is determined by its associated evolution semispray. We uniquely determine this semispray using the symplectic structure and the energy of the Lagrange space and the external force field. We study the variation of the energy and Lagrangian functions along the evolution and…

Finite time for subsolutions on Riemannian manifolds proved.

Using the result by D.Gessler (Differential Geom. Appl. 7 (1997) 303-324, DIPS-9/98, http://diffiety.ac.ru/preprint/98/09_98abs.htm), we show that any invariant variational bivector (resp., variational 2-form) on an evolution equation with nondegenerate right-hand side is Hamiltonian (resp., symplectic).

New framework uses PDE for no-regret generative modeling.

The extragradient method fails for hypomonotone variational inequalities.

Introduces new gradient-based methods for machine learning problems.

Method learns latent dynamics of complex systems from noisy data.

Extends tracking guarantees for time-varying variational inequalities.

Study finds loops with specific curvature exist using Hardy's inequality.

We show that an infinite dimensional Lie group in Milnor's sense has the strong Trotter property if it is locally $μ$-convex. This is a continuity condition imposed on the Lie group multiplication that generalizes the triangle inequality for locally convex vector spaces, and is equivalent to $C^0$-continuity of the evo…

New method learns low-dimensional representations of nonlinear time series without supervision.

Study intrinsic volume forms on complex hypersurfaces.

New proof of Gaffney's inequality for differential forms on manifolds with boundary.

Algorithm learns latent variables for thermodynamically-consistent deep neural networks.

$f$-divergences are a general class of divergences between probability measures which include as special cases many commonly used divergences in probability, mathematical statistics and information theory such as Kullback-Leibler divergence, chi-squared divergence, squared Hellinger distance, total variation distance e…

In this paper we are concerned with the learnability of energies from data obtained by observing time evolutions of their critical points starting at random initial equilibria. As a byproduct of our theoretical framework we introduce the novel concept of mean-field limit of critical point evolutions and of their energy…