Develops inequalities for high-dimensional linear processes with dependent innovations.
problem Estimating high-dimensional VAR(p) systems and HAC covariance estimation.
method Concentration inequalities for l∞ norm of vector linear processes with sub-Weibull, mixingale innovations. result Obtained concentration bounds for the maximum entrywise norm of lag-h autocovariance matrices. Linear inequality found for certain curved spaces.
problem Finding isoperimetric inequalities for curved spaces.
method Extending known result to homogeneous Hadamard manifolds.
result Linear isoperimetric inequality proven for higher-dimensional cycles.
We give a geometric interpretation of the linear trace Harnack inequality for the Ricci flow.
The paper studies optimal transport in linear quadratic systems and derives interpolation inequalities.
problem Optimal transport problem in Linear Quadratic optimal control systems.
method Well-posedness of the Monge problem, regularity of optimal transport map, displacement interpolation of measures.
result Derivation of general interpolation inequalities for entropy functionals.
The paper establishes new inequalities for Finsler measure spaces.
problem Developing inequalities for Finsler measure spaces.
method Study of linearized heat semigroup and application of Li-Yau's inequalities.
result Established new Li-Yau's type inequalities for Finsler measure spaces.
Extends Gaussian process approach to handle linear inequality constraints.
problem Real-world problems with inequality constraints.
method Finite-dimensional Gaussian approach with linear inequality constraints, MCMC techniques.
result Efficient results on data fitting and uncertainty quantification.
Unified approach to discrete and smooth isoperimetric inequalities of arbitrary order.
problem Finding higher order isoperimetric inequalities for both discrete and smooth curves.
method Unified approach via Fourier analysis of linear operators.
result Unified upper and lower bounds for isoperimetric deficit in smooth curves.
We introduce a new version of a curvature-dimension inequality for non-negative curvature. We use this inequality to prove a logarithmic Li-Yau inequality on finite graphs. To formulate this inequality, we introduce a non-linear variant of the calculus of Bakry and Émery. In the case of manifolds, the new calculus and …
Tutorial on using concentration inequalities for linear system identification.
problem Learning state-space parameters of linear systems.
method Large-deviations and self-normalized martingales.
result Data-dependent and independent bounds on learning rate.
Sharp bounds on uniform generalization errors in binary linear classification.
problem Understanding the uniform generalization errors in binary linear classification.
method Isoperimetric arguments, Poincaré and log-Sobolev inequalities for joint distributions.
result Sharp concentration bounds on uniform generalization errors, almost sure convergence in broad settings.
Polyak-Łojasiewicz inequality simplifies linear convergence proofs.
problem Proving linear convergence without strong convexity.
method Using Polyak-Łojasiewicz inequality to analyze various optimization methods.
result New analyses and proofs of linear convergence for multiple machine learning problems.
Paper introduces structured sparsity estimators for Generalized Linear Models.
problem Estimating structured sparsity in GLMs with debiased estimators.
method Extends Stucky and van de Geer's results to GLMs with structured sparsity.
result Proves oracle inequalities for structured sparsity estimators in GLMs.
The paper proves waist inequalities for convex bodies and their linear images.
problem Understanding geometric characteristics of convex bodies through waist inequalities.
method Connections between Gromov's and Milman's work, proving waist inequalities for convex bodies and their linear images.
result Any convex body has a linear image satisfying a waist inequality with a universal constant.
This paper proves AdaGrad and Adam converge linearly under PL inequality.
problem Understanding the convergence of adaptive gradient methods.
method Unified approach proving AdaGrad and Adam converge linearly under PL inequality.
result AdaGrad and Adam converge linearly when the cost function is smooth and satisfies PL inequality.
Study interior estimates for solutions of Poisson equation on Riemann surfaces.
problem Interior estimates for solutions of linear Poisson equation on Riemann surfaces.
method Used Zygmund space LlnL and isoperimetric inequality. result Derived interior estimates, Harnack inequalities, and global estimate.
The paper explores inequalities and generalizations of gradient Ricci solitons.
problem Inequalities and generalizations of gradient Ricci solitons.
method Proposes generalizations of Ricci solitons to manifolds with linear connections.
result Provides relationships between curvature and scalar field through equations.
We introduce a Bernstein-type inequality which serves to uniformly control quadratic forms of gaussian variables. The latter can for example be used to derive sharp model selection criteria for linear estimation in linear regression and linear inverse problems via penalization, and we do not exclude that its scope of a…
We prove several differential Harnack inequalities for positive solutions to nonlinear backward heat equations with different potentials coupled with the Ricci flow. We also derive an interpolated Harnack inequality for the nonlinear heat equation under the ε-Ricci flow on a closed surface. These new Harnac…
Study shows long-term solutions for complex equations on curved spaces.
problem Long-term behavior of solutions to fully non-linear parabolic equations on Hermitian manifolds.
method Used general assumptions and derived a Harnack inequality for the linearized equation.
result Proved the long-time existence and convergence of solutions.
New method estimates GGLM parameters, overcoming non-convexity.
problem Estimating parameters in GGLM with dependencies.
method Monotone operator-based variational inequality method.
result Guarantees for parameter recovery in GLM and GGLM.
We describe the set of possible vector valued side lengths of n-gons in thick Euclidean buildings of rank 2. This set is determined by a finite set of homogeneous linear inequalities, which we call the generalized triangle inequalities. These inequalities are given in terms of the combinatorics of the spherical Coxeter…
Neural networks solve variational inequalities for optimal stopping problems.
problem Solving variational inequalities for optimal stopping problems in finance.
method Proposed neural network approach using loss functions directly incorporating variational inequality on whole domain.
result Existence and convergence of neural networks whose losses converge to zero.
Disproves Fedotov's conjecture on higher-order Shephard inequalities.
problem Fedotov's conjecture on higher-order Shephard inequalities.
method Using Hodge-Riemann relations for simple convex polytopes.
result Fedotov's conjecture is disproved.
Random complexes can be embedded linearly if certain conditions on parameters are met.
problem Embedding random simplicial complexes linearly in Euclidean space.
method Established strict inequalities on parameters for linear embedding into R^(2d).
result Necessary and sufficient conditions for linear embedding of random complexes.
The study proves a gap theorem for CAT(0) spaces with a constant below 1/(6√π).
problem Proving isoperimetric inequalities in non-positive curvature spaces.
method Introduced minimal tetrahedra to prove a linear inequality.
result Established a gap theorem for CAT(0) spaces with a constant below 1/(6√π).
This paper approximates Gaussian process emulators with constraints and noisy data.
problem Realistic stochastic emulators with inequality constraints and noisy observations.
method Monte Carlo and Markov Chain Monte Carlo methods with noise term.
result Improved performance of MC and MCMC samplers with noisy observations and constraints.
AdaGrad-Norm achieves linear convergence for certain functions.
problem Proving linear convergence for specific types of functions.
method Introducing RUIG, a measure of gradient balance; developing a two-stage framework.
result AdaGrad-Norm achieves linear convergence for certain functions.
In this paper we prove general inequalities involving the weighted mean curvature of compact submanifolds immersed in weighted manifolds. As a consequence we obtain a relative linear isoperimetric inequality for such submanifolds. We also prove an extrinsic upper bound to the first non zero eigenvalue of the drift Lapl…
New proof of Riemannian Penrose Inequality for manifolds with corners
problem Riemannian Penrose Inequality for asymptotically flat manifolds with corners
method Unified argument based on approximate monotonicity
result Positive Mass Theorem and Riemannian Penrose Inequality
New inequality for regression risk with random design and noise.
problem Excess risk in least-squares regression with random design and heteroscedastic noise.
method Proved a new concentration inequality for the excess risk in least-squares regression with random design and heteroscedastic noise, separating linearized and quadratic processes.
result Generalized the approach to quadratic contrasts and random design.
On a Riemannian metric-measure space, we establish an Alexandrov-Bakelman-Pucci type measure estimate connecting Bakry-Émery Ricci curvature lower bound, modified Laplacian and the measure of certain special sets. We apply this estimate to prove Harnack inequalities for the modified Laplacian operator and fully non-lin…
Study shows how many samples are needed for accurate predictions with graph-structured sparsity.
problem Finding the minimum number of samples for accurate sparse vector recovery.
method Used Fano's inequality on graph-structured ensembles to establish lower bounds.
result Proved necessary number of samples for weighted graph model.
The aim of this paper is to prove isoperimetric inequalities on submanifolds of the Euclidean space using mass transportation methods. We obtain a sharp ?weighted isoperimetric inequality? and a nonsharp classical inequality similar to the one obtained by J. Michael and L. Simon. The proof relies on the description of …
The paper finds inequalities for eigenvalues of fourth order elliptic operators on Riemannian manifolds.
problem Eigenvalue inequalities for fourth order elliptic operators on Riemannian manifolds.
method Analyzes eigenvalues of fourth order elliptic operators in divergence form with Dirichlet boundary conditions on bounded domains in compact Riemannian manifolds.
result General inequalities for eigenvalues are derived.
The paper generalizes the Cauchy-Schwarz-Bunyakovsky inequality and applies it to elasticity problems.
problem Applying the Cauchy-Schwarz-Bunyakovsky inequality to elasticity problems.
method Presentation of discrete and integral forms, n-dimensional generalizations, and strengthened CBS inequality.
result The strengthened CBS inequality is crucial for elasticity problems.
We prove a linear trace Li-Yau-Hamilton inequality for the Kaehler-Ricci flow. We then use this sharp differential inequality to study the Liouville properties of the plurisubharmonic functions on complete Kaehler manifolds with nonnegative bisectional curvature.
Proposes a method to impose linear inequality constraints on neural networks.
problem Imposing prior knowledge on neural network activations.
method Directly incorporates constraints into the network architecture using stochastic gradient descent.
result Significantly speeds up inference at test time with up to two orders of magnitude improvement.
Gradient bounds and Liouville theorems for quasi-linear equations on manifolds with nonnegative Ricci curvature.
problem Establishing bounds and theorems for solutions to quasi-linear elliptic equations on compact manifolds with nonnegative Ricci curvature.
method Gradient bounds, Liouville-type theorems, local splitting theorem, Harnack-type inequality, ABP estimate.
result Gradient bounds and Liouville-type theorems for solutions to quasi-linear equations on compact manifolds with nonnegative Ricci curvature.
The paper develops new inequalities for Markov chain sums, linking them to mixing time.
problem Establishing concentration inequalities for Markov chain sums.
method Developed novel concentration inequalities for geometrically ergodic Markov chains, linking bounds to mixing time constants.
result Explicit bounds for additive functionals of Markov chains, linked to Rosenthal inequality constants and mixing properties.
We establish refinements of the classical Kato inequality for sections of a vector bundle which lie in the kernel of a natural injectively elliptic first-order linear differential operator. Our main result is a general expression which gives the value of the constants appearing in the refined inequalities. These consta…
Proves homological inequality for cycles in Hadamard spaces of asymptotic rank 2.
problem Establishing isoperimetric inequalities in Hadamard spaces of asymptotic rank two.
method Homological inequality for cycles in dimensions at least 2, assuming finite linearly controlled asymptotic dimension.
result Homological inequality for general cycles in Hadamard 3-manifolds and finite-dimensional CAT(0) cube complexes.
The paper proves inequalities and formulas for submanifolds in specific warped product manifolds.
problem Understanding geometric properties of submanifolds in warped product manifolds.
method Proving linear isoperimetric inequalities and monotonicity formulas for submanifolds with bounded mean curvature vector.
result Lower bound estimates for the volume of submanifolds in terms of the warping function.
Article provides conditions for spherical metrics with conical singularities.
problem Existence of metrics with conical singularities on a 2-sphere.
method Criterion based on linear inequalities in prescribed angles.
result Necessary and sufficient condition for metric existence.
We obtain a maximum principle, and "a priori" upper estimates for solutions of a class of non linear singular elliptic differential inequalities on Riemannian manifolds under the sole geometrical assumption of volume growth conditions. Various applications of the results obtained are presented.
The paper studies Harnack inequalities on Finsler metric measure spaces.
problem Analyzing Harnack inequalities on Finsler metric measure spaces.
method Using weighted Ricci curvature and distortion conditions, the authors derive an elliptic p-Harnack inequality.
result The paper establishes an elliptic p-Harnack inequality and derives Hölder continuity and gradient estimates for positive harmonic functions.
Study non-Gaussian measures' concentration properties in metric spaces.
problem Concentration properties for non-linear Gaussian functionals with non-Gaussian tails.
method Prove generalised Transportation-Cost Inequalities (TCIs) for specific functionals.
result Extended TCIs for rough volatility and Parabolic Anderson Model.
This paper consider penalized empirical loss minimization of convex loss functions with unknown non-linear target functions. Using the elastic net penalty we establish a finite sample oracle inequality which bounds the loss of our estimator from above with high probability. If the unknown target is linear this inequali…
This paper develops basic setting for the dual Orlicz-Brunn-Minkowski theory for star bodies. An Orlicz φ-radial addition of two or more star bodies is proposed and related dual Orlicz-Brunn-Minkowski inequality is established. Based on a linear Orlicz φ-radial addition of two star bodies, we derive a f…