The paper extends log-Sobolev inequalities to matrix-valued settings using combinatorial methods.
problem Log-Sobolev inequalities for matrix-valued settings.
method Combining noncommutative geometry tools and combinatorial methods.
result Combinatorial methods yield computable lower bounds for matrix-valued log-Sobolev inequalities.
The study proves inequalities and curvature properties for Markov chains.
problem Isoperimetric and concentration inequalities for Markov chains.
method Laplacian separation principle for eikonal equation; modified log-Sobolev constant; Ollivier curvature.
result Affirmative answers to open questions and new inequalities.
LMC algorithm receives first convergence guarantees under weak smoothness conditions.
problem Convergence guarantees for LMC under weak smoothness conditions.
method Using Latała--Oleszkiewicz or modified log-Sobolev inequalities.
result First convergence guarantees for LMC under weak smoothness conditions.
The paper derives Harnack inequalities for evolving Riemannian manifolds without dimensionality restrictions.
problem Deriving Harnack inequalities for geometric flows with evolving metrics.
method Probabilistic representation of conjugate semigroups and supercontractivity.
result Established dimension-free Harnack inequalities for geometric flows.
Log-Sobolev inequality proven for submanifolds in specific types of manifolds.
problem Proving Log-Sobolev inequality for submanifolds in asymptotic non-negative intermediate Ricci curvature manifolds.
method Extending previous results, proving inequality for submanifolds in specific types of manifolds.
result Sharp Log-Sobolev inequality proven for submanifolds in complete non-compact Riemannian manifolds with asymptotic non-negative intermediate Ricci curvature and Euclidean volume growth.
Sharp log-Sobolev inequalities proved for C D ( 0 , N ) {\sf CD}(0,N) CD ( 0 , N ) spaces.
problem Proving log-Sobolev inequalities in noncompact metric measure spaces.
method Sharp isoperimetric inequality, symmetrisation, scaling argument, Hamilton-Jacobi inequality, Sobolev regularity.
result Sharp log-Sobolev inequalities established in C D ( 0 , N ) {\sf CD}(0,N) CD ( 0 , N ) spaces. Log Sobolev and Michael Simon inequalities for tensor fields on curved manifolds.
problem Establishing inequalities for tensor fields on curved manifolds.
method Applying the ABP method to symmetric tensor fields on manifolds with nonnegative sectional curvature.
result Log Sobolev and Michael Simon inequalities for tensor fields.
The paper derives inequalities and formulas for generalized Ricci flow.
problem Understanding and characterizing generalized Ricci flow.
method Using Bochner formula and adapted Malliavin gradient, the paper derives inequalities and characterizes generalized Ricci flow.
result Characterizations of generalized Ricci flow via inequalities for the associated Malliavin gradient.
We derive weighted log-Sobolev inequalities from a class of super Poincaré inequalities. As an application, the Talagrand inequality with larger distances are obtained. In particular, on a complete connected Riemannian manifold, we prove that the $\log^\dd$ -Sobolev inequality with $\dd\in (1,2)$ implies the $L^{2/(2-\d…
Unified analysis of MPLE for Ising models with bounded operator norm or infinity norm.
problem Estimating Ising models in Total Variation distance with limited samples.
method Maximum Pseudo-Likelihood Estimator (MPLE) for two general classes of Ising models.
result Unified framework for polynomial-time estimation in TV distance for two general classes of Ising models.
In this paper, we prove the equivalent of ultracontractive bound of heat semigroup or the uniform upper bound of the heat kernel with the Nash inequality, Log-Sobolev inequalities on graphs. We also show that under the assumption of volume growth and nonnegative curvature C D E ′ ( n , 0 ) CDE'(n,0) C D E ′ ( n , 0 ) the Sobolev inequality, Nash inequa…
Improved sampling from non-log-concave distributions with polynomial query complexity.
problem Sampling from distributions with non-log-concave densities efficiently.
method Combining Ornstein-Uhlenbeck process assumptions and polynomial moment conditions.
result Polynomial query complexity improvement over previous methods.
New deficit functions link elliptic and parabolic inequalities, proving log Sobolev.
problem Proving log Sobolev inequality using deficit functions.
method Introducing two deficit functions, one elliptic and one parabolic, and showing their pointwise convergence and equations.
result Elliptic deficit converges to parabolic deficit, leading to an elliptic proof of log Sobolev inequality.
New sampling and identity-testing methods for mixtures of distributions that don't satisfy approximate tensorization of entropy.
problem Sampling and identity-testing for mixtures of distributions that don't satisfy approximate tensorization of entropy.
method Fast mixing of Glauber dynamics and efficient identity-testers in the coordinate-conditional sampling access model.
result Efficient identity-testers for mixtures of ATE distributions in the coordinate-conditional sampling access model.
New framework improves EM algorithm convergence under log-Sobolev inequality.
problem Improving convergence of the EM algorithm.
method Extending gradient flow techniques to EM algorithm, using free energy representation.
result Exponential convergence of EM algorithm under log-Sobolev inequality.
New algorithm samples superlinearly growing log-gradient distributions.
problem Sampling from distributions with superlinearly growing log-gradient.
method Proposes a novel taming Langevin-based scheme called sTULA.
result Derives non-asymptotic convergence bounds in KL, TV, and W2 distances.
The study establishes inequalities on path space for sub-Riemannian manifolds.
problem Understanding functional inequalities on path space for sub-Riemannian manifolds.
method Derivative and integration by parts formulae on path space with respect to a natural gradient operator, showing bounds of horizontal Ricci curvature.
result Established functional inequalities on path space analogous to Riemannian geometry.
Study non-negative curvature Markov chains, proving entropy contraction.
problem Prove entropy contraction for Markov chains with non-negative curvature.
method Prove 1-step contraction in Wasserstein distance implies 1-step contraction in relative entropy.
result Prove MLSI with constant equal to minimal rate increment for mean-field zero-range process.
The study improves Poincaré and log-Sobolev inequalities on hyperbolic spaces.
problem Improving Poincaré and log-Sobolev inequalities on hyperbolic spaces.
method Establishing scale-dependent Poincaré-Hardy type identities and choosing suitable parameters, potentials, and vector fields.
result Derives new versions and substantially improves existing inequalities.
Proves error bounds for PGD, extending log-Sobolev and Talagrand inequalities.
problem Maximum likelihood estimation of large latent variable models.
method Extending log-Sobolev and Talagrand inequalities to models with strongly concave log-likelihoods.
result Non-asymptotic error bounds for PGD in models satisfying LSI and PŁI.
Let P t P_t P t be the diffusion semigroup generated by L : = Δ + ∇ V L:=Δ+\nabla V L := Δ + ∇ V on a complete connected Riemannian manifold with Ric ≥ − ( σ 2 ρ o 2 + c ) \operatorname {Ric}\ge-(σ^2ρ_o^2+c) Ric ≥ − ( σ 2 ρ o 2 + c ) for some constants σ , c > 0 σ, c>0 σ , c > 0 and ρ o ρ_o ρ o the Riemannian distance to a fixed point. It is shown that P t P_t P t is hypercontractive, or the log-Sobolev inequality holds for the…
We develop a Malliavin calculus on the horizontal path space of a totally geodesic Riemannian foliation. As a first application, under suitable assumptions, we prove a log-Sobolev inequality for a natural one-parameter family of infinite-dimensional Ornstein-Uhlenbeck type operators. As a second application, we obtain …
Improved Langevin algorithms with prior diffusion achieve dimension-independent convergence for non-log-concave distributions.
problem Understanding the dimension dependency of computational complexity in high-dimensional sampling.
method Investigation of prior diffusion technique for log-Sobolev inequality target distributions.
result Modified Langevin algorithm achieves dimension-independent KL divergence convergence.
New sampling algorithms for complex distributions without log-concavity.
problem Efficient sampling from complex, high-dimensional distributions.
method Randomized splitting Langevin Monte Carlo (RSLMC) algorithm.
result Uniform-in-time error bounds for RSLMC and RLMC algorithms.
Inequalities linking entropy, Fisher info, Stein discrepancy, and Wasserstein distance on Riemannian manifolds.
problem Linking entropy, Fisher info, Stein discrepancy, and Wasserstein distance on Riemannian manifolds.
method Deriving inequalities linking these measures on Riemannian manifolds.
result Strengthening and extending existing inequalities to Riemannian manifolds.
Paper disproves conjecture about log-Sobolev constants.
problem Log-Sobolev constants and curvature bounds.
method Counterexample on birth-death chains.
result Conjecture about Ollivier curvature is incorrect.
Given a probability measure μ μ μ supported on a convex subset Ω Ω Ω of Euclidean space ( R d , g 0 ) (\mathbb{R}^d,g_0) ( R d , g 0 ) , we are interested in obtaining Poincaré and log-Sobolev type inequalities on ( Ω , g 0 , μ ) (Ω,g_0,μ) ( Ω , g 0 , μ ) . To this end, we change the metric g 0 g_0 g 0 to a more general Riemannian one g g g , adapted in a certain sense to μ μ μ , and perform…
Let $\M$ be a complete, connected noncompact manifold with bounded geometry. Under a condition near infinity, we prove that the Log Sobolev functional (\ref{logfanhan}) has an extremal function decaying exponentially near infinity. We also prove that an extremal function may not exist if the condition is violated. This…
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.
We study the Unadjusted Langevin Algorithm (ULA) for sampling from a probability distribution ν = e − f ν= e^{-f} ν = e − f on R n \mathbb{R}^n R n . We prove a convergence guarantee in Kullback-Leibler (KL) divergence assuming ν ν ν satisfies a log-Sobolev inequality and the Hessian of f f f is bounded. Notably, we do not assume convexity or boun…
Study establishes Pólya-Szegő inequalities on submanifolds with small total mean curvature.
problem Analyzing Sobolev functions on submanifolds with curvature constraints.
method Developed Pólya-Szegő-type inequalities and derived corollaries.
result Proved sharp p p p -Log-Sobolev inequality for minimal submanifolds. Proposes a new generalization bound for Bayesian deep nets without strict assumptions.
problem Lack of generalization bounds for Bayesian deep nets without strict assumptions.
method Exploits contractivity of Log-Sobolev inequalities to add a loss-gradient norm term to the generalization bound.
result Introduces a new generalization bound for Bayesian deep nets that avoids strict assumptions.
Our work improves Langevin dynamics convergence on manifolds.
problem Sampling from distributions defined on manifolds.
method Generalized Langevin dynamics to manifolds, proving KL decrease rate.
result KL divergence decreases geometrically on manifolds with log-Sobolev inequality.
PLA improves sampling from distributions under isoperimetry with faster KL divergence convergence.
problem Sampling from distributions with KL divergence under isoperimetry.
method Proximal Langevin Algorithm (PLA) with KL and Rényi divergence convergence guarantees.
result PLA achieves faster KL divergence convergence rates than ULA under log-Sobolev inequality.
Paper proposes new Langevin samplers for sampling from log-concave distributions with superlinear gradient growth.
problem Sampling from log-concave distributions with superlinear gradient growth.
method Proposes two novel discretizations of kinetic Langevin SDEs, showing contractivity and log-Sobolev inequality.
result Establishes non-asymptotic bounds in 2-Wasserstein distance between sampled distributions and target measures.
Greedy MI maximization method outperforms existing approaches in nonlinear models.
problem Maximizing mutual information in nonlinear models with non-Gaussian noise.
method Greedy approaches based on log-Sobolev inequalities for computationally inexpensive MI lower bounds.
result Proposed method outperforms random selection and Gaussian approximations.
The paper proves optimizability implies inequalities for sampling.
problem Optimizing functions via Gradient Flow and sampling from Gibbs measures.
method Gradient Flow and Lyapunov potentials to establish inequalities.
result Optimizability via Gradient Flow implies Poincaré and Log-Sobolev Inequalities.
Sharp Lipschitz bounds for flow-matching and diffusion models with optimal sampling rates.
problem Establishing optimal Lipschitz regularity for flow-matching and diffusion models.
method Sharp Lipschitz regularity theory for flow-matching vector fields and diffusion-model scores.
result Achieves optimal sampling rate of d / N \sqrt{d}/N d / N for Euler-type samplers in dimension d d d . Derives sub-Riemannian Ricci curvature for various manifolds.
problem Calculating Ricci curvature in sub-Riemannian geometry.
method Generalized Gamma z z z calculus and z z z --Bochner's formula. result Analytical bounds for sub-Riemannian curvature dimension and log-Sobolev inequalities.
We define a Hamilton-Jacobi semigroup acting on continuous functions on a compact length space. Following a strategy of Bobkov, Gentil and Ledoux, we use some basic properties of the semigroup to study geometric inequalities related to concentration of measure. Our main results are that (1) a Talagrand inequality on a …
New bound relaxes uniform gradient norm assumptions for PAC-Bayesian bounds.
problem Generalization bounds with strict assumptions like uniformly bounded loss.
method Relax uniform bounds assumptions to on-average bounded loss and gradient norm.
result Proposes a new generalization bound with a surrogate of model complexity.
Improved Langevin Monte Carlo reduces energy barriers for faster optimization.
problem Optimizing functions with high energy barriers.
method Proposes a modified landscape for Langevin Monte Carlo.
result Polynomial dependence on energy barrier in Log-Sobolev constant.
New method samples from non-log-concave distributions with weak dissipativity.
problem Sampling from distributions that are not log-concave and weakly dissipative.
method Taming scheme tailored to growth and decay properties of the target distribution.
result Explicit non-asymptotic guarantees for KL, TV, and Wasserstein distances.
Extends Langevin dynamics for constrained domains.
problem Optimization of constrained probability measures.
method Mirror mean-field Langevin dynamics (MMFLD).
result Linear convergence guarantees and propagation of chaos results.
In this note we prove a new ε-regularity theorem for the Ricci flow. Let (M^n,g(t)) with t\in [-T,0] be a Ricci flow and H_{x} the conjugate heat kernel centered at a point (x,0) in the final time slice. Substituting H_{x} into Perelman's W-functional produces a monotone function W_{x}(s) of s \in [-T,0], the pointed e…
Mirror Langevin Algorithm converges with zero bias.
problem Achieving convergence with zero bias in discrete-time sampling.
method Discretization of Mirror Langevin Diffusion and mean-square analysis.
result Mirror Langevin Algorithm converges with zero bias.
Improved sampling from mean-field stationary distributions.
problem Sampling from the stationary distribution of mean-field SDEs.
method Decoupling the problem into two aspects: approximation of mean-field SDE and sampling from finite-particle distribution.
result Improved guarantees in various settings, including optimizing neural networks.
The Riemannian Langevin Algorithm samples from manifolds efficiently.
problem Sampling from distributions on manifolds with log-Sobolev inequality.
method Riemannian Langevin Algorithm, log-Sobolev inequality, self-concordance extension, stochastic smoothness bounding.
result The Riemannian Langevin Algorithm converges rapidly to the target density.