Zigzag sampling algorithm efficiently samples from strongly log-concave distributions with low computational cost.
problem Sampling from strongly log-concave distributions efficiently and with low computational complexity.
method Zigzag sampling algorithm with warm start assumption, focusing on gradient evaluations.
result Achieves ε error in chi-square divergence with computational cost of O(κ²d^(1/2)(log(1/ε))^(3/2)) gradient evaluations.
Introduces CSLC models to bridge deep generative models and classical algorithms.
problem Mode collapse and memorization issues in deep generative models and restrictive assumptions in classical algorithms.
method Introduces conditionally strongly log-concave (CSLC) models, factorizing data distribution into strongly log-concave conditional distributions.
result Efficient parameter estimation and sampling algorithms with theoretical guarantees for non-log-concave data distributions.
Gibbs sampler contracts entropy under strong log-concavity, improving mixing time.
problem Improving the mixing time of Gibbs sampler under strong log-concavity.
method Analyzing Gibbs sampler contraction under strong log-concavity, providing sharp contraction rate.
result Gibbs sampler contracts entropy linearly with condition number and independent of dimension under strong log-concavity.
Log-concavity of eigenfunctions on curved surfaces is proven, leading to fundamental gap estimates.
problem Proving log-concavity of eigenfunctions on curved surfaces.
method Analyzing the Laplacian eigenfunctions on positively curved surfaces.
result Strong log-concavity of the first eigenfunction on positively curved surfaces.
Strongly log-concave (SLC) distributions are a rich class of discrete probability distributions over subsets of some ground set. They are strictly more general than strongly Rayleigh (SR) distributions such as the well-known determinantal point process. While SR distributions offer elegant models of diversity, they lac…
New algorithms sample from log concave distributions without gradient Lipschitz continuity.
problem Sampling from log concave distributions without gradient Lipschitz continuity.
method Two algorithms based on monotone polygonal (tamed) Euler schemes.
result Non-asymptotic 2-Wasserstein distance bounds between the process and target measure.
Study on Wasserstein distance for numerical approximations of stochastic differential equations.
problem Estimating the Wasserstein distance between stochastic differential equation distributions and their numerical approximations.
method Unified framework for analyzing different integrators and a novel splitting method for underdamped Langevin dynamics.
result A novel splitting method for underdamped Langevin dynamics with optimal complexity.
CAVI converges for log-concave measures via optimal transport.
problem Finding the closest product measure to a log-concave measure via CAVI.
method Adapting coordinate descent techniques from Euclidean space to optimal transport for log-concave densities.
result Proves convergence of CAVI for log-concave densities and provides rates of convergence under additional conditions.
New Langevin method achieves third order convergence for strongly log-concave distributions.
problem Sampling from complex distributions efficiently.
method Underdamped Langevin diffusion with third order convergence.
result Achieves 2-Wasserstein error of ε in O(√d/ε^1/3) steps under additional Lipschitz condition.
New lower bounds for sampling from log-concave distributions in higher dimensions.
problem Proving lower bounds for sampling from log-concave distributions in higher dimensions.
method Multiscale construction inspired by geometric measure theory and reduction to block Krylov algorithms.
result Query lower bounds for sampling from log-concave distributions in higher dimensions are established.
Algorithm samples from composite log-concave distributions using gradient evaluations and restricted Gaussian oracles.
problem Sampling from composite log-concave distributions with limited gradient evaluations.
method Proximal gradient algorithm with RGO for g g g and strong/strongly convex conditions for f f f . result Achieves ε ε ε error in total variation distance in O ~ ( κ d log 4 ( 1 / ε ) ) \widetilde{\mathcal O}(κ\sqrt d \log^4(1/ε)) O ( κ d log 4 ( 1/ ε )) iterations. New algorithms estimate normalizing constants for log-concave distributions efficiently.
problem Estimating the normalizing constant of log-concave distributions.
method Annealing algorithm combined with multilevel Monte Carlo method based on underdamped Langevin dynamics.
result At least d 1 − o ( 1 ) ε 2 − o ( 1 ) \frac{d^{1-o(1)}}{\varepsilon^{2-o(1)}} ε 2 − o ( 1 ) d 1 − o ( 1 ) queries are necessary, and O ~ ( d 4 / 3 κ + d 7 / 6 κ 7 / 6 ε 2 ) \widetilde{\mathcal{O}}\Bigl(\frac{d^{4/3}κ+ d^{7/6}κ^{7/6}}{\varepsilon^2}\Bigr) O ( ε 2 d 4/3 κ + d 7/6 κ 7/6 ) queries are sufficient. 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.
ULA estimates covariance of log-concave distributions efficiently.
problem Estimating covariance matrices of log-concave distributions efficiently.
method Unadjusted Langevin algorithm (ULA) for sampling and covariance estimation.
result Sample complexity of single-chain ULA is smaller than that of parallel ULA by a logarithmic factor.
RHMC accelerates sampling from log-concave distributions.
problem Sampling from log-concave probability distributions efficiently.
method RHMC uses simulated Hamiltonian dynamics with random integration times.
result RHMC converges exponentially fast in KL divergence for log-concave distributions.
Lower bounds show many sampling algorithms need many gradient queries.
problem Sampling from strongly log-concave densities in high dimensions.
method Information theory and stochastic gradient methods.
result Lower bound on number of gradient queries needed.
MALA mixes optimally in κ√d steps for log-concave sampling.
problem Sampling from log-concave distributions efficiently.
method Metropolis-Adjusted Langevin Algorithm (MALA) with warm start.
result Optimal minimax mixing time of κ√d iterations for log-concave distributions.
Improved sampling algorithm with state-of-the-art complexity bounds.
problem Efficient sampling from various probability distributions.
method Proximal sampler with inexact restricted Gaussian oracle.
result State-of-the-art complexity bounds in almost all settings.
A new sampling method reduces computational cost for high-dimensional log-concave distributions.
problem High computational cost of ULMC in high dimensions.
method Random Coordinate ULMC (RC-ULMC) selects a single coordinate per iteration.
result RC-ULMC is cheaper than classical ULMC, especially in highly skewed and high-dimensional problems.
For sampling from a log-concave density, we study implicit integrators resulting from θ θ θ -method discretization of the overdamped Langevin diffusion stochastic differential equation. Theoretical and algorithmic properties of the resulting sampling methods for θ ∈ [ 0 , 1 ] θ\in [0,1] θ ∈ [ 0 , 1 ] and a range of step sizes are established. Ou…
New method improves sampling for weakly log-concave posteriors.
problem Sampling from weakly log-concave posterior distributions.
method Stochastic Langevin Monte Carlo with over-damped diffusion.
result Simulation horizon is ( d log ( n ) 2 ) ( 1 + r ) 2 (d \log(n)^2)^{(1+r)^2} ( d log ( n ) 2 ) ( 1 + r ) 2 with Poisson subsampling. The paper studies stability of mean-field variational inference for log-concave distributions.
problem Stability of mean-field variational inference for log-concave distributions.
method Novel approach via linearized optimal transport, lifting non-convex problem to convex optimization over transport maps.
result Dimension-free Lipschitz continuity of the MFVI optimizer with respect to the target distribution, measured in 2-Wasserstein distance.
Efficient algorithm for learning halfspaces in a new model with polynomial time complexity.
problem Learning halfspaces in the testable learning model with distributional constraints.
method Developed new tests using labels and combined with moment-matching approach.
result Achieved near optimal error rates for Gaussian and strongly log-concave distributions.
The unadjusted Langevin algorithm converges faster for some variables in high dimensions.
problem Sampling probability distributions in high-dimensional settings.
method Analysis of the unadjusted Langevin algorithm for strongly log-concave distributions.
result The delocalization of bias effect allows for faster convergence for a small number of variables.
Paper proves generalized Talagrand inequality for Sinkhorn distance.
problem Proving a generalized Talagrand inequality for Sinkhorn distance.
method Using entropy power inequality and infinitesimal displacement convexity of optimal transport map.
result Extends previous results of Gaussian Talagrand inequality for Sinkhorn distance to strongly log-concave case.
Gibbs sampler mixes quickly for certain smooth distributions.
problem Drawing samples from log-smooth log-concave distributions.
method Analyzes Gibbs sampler on log-smooth and strongly log-concave distributions.
result Gibbs sampler mixes in O ⋆ ( κ 2 n 7.5 ) O^{\star}(κ^2 n^{7.5}) O ⋆ ( κ 2 n 7.5 ) steps. Improved log-concave sampling to O ( d 1 / 2 ) O(d^{1/2}) O ( d 1/2 ) with warm starts.
problem Sampling from strongly log-concave distributions efficiently.
method Warm starts and discretized underdamped Langevin diffusion.
result Achieved O ( d 1 / 2 ) O(d^{1/2}) O ( d 1/2 ) complexity for high-accuracy sampling. A new framework RTK accelerates diffusion inference by breaking down the process into fewer, more efficient subproblems.
problem Efficiently generating data from trained diffusion models using discretized reverse SDEs or ODEs.
method Developed a general RTK framework that decomposes the diffusion process into fewer, more balanced subproblems, using MALA and ULD for sampling.
result The RTK-MALA and RTK-ULD algorithms achieve faster convergence rates and lower error compared to existing methods.
We propose a fast stochastic Hamilton Monte Carlo (HMC) method, for sampling from a smooth and strongly log-concave distribution. At the core of our proposed method is a variance reduction technique inspired by the recent advance in stochastic optimization. We show that, to achieve ε ε ε accuracy in 2-Wasserstein distanc…
Hamiltonian Monte Carlo (HMC) is a widely deployed method to sample from high-dimensional distributions in Statistics and Machine learning. HMC is known to run very efficiently in practice and its popular second-order "leapfrog" implementation has long been conjectured to run in d 1 / 4 d^{1/4} d 1/4 gradient evaluations. Here we …
BBVI converges nearly dimensionally independent for log-concave targets.
problem Efficiently optimizing variational parameters in high-dimensional spaces.
method Proved convergence rate of BBVI with reparametrization gradient for log-concave targets.
result BBVI converges with nearly independent dimension dependence for log-concave targets.
New method uses higher-order Langevin dynamics for efficient parallel sampling.
problem Efficient parallel sampling from high-dimensional log-concave distributions.
method Combines higher-order Langevin dynamics with blockwise Lagrange polynomial interpolation.
result Reduces the number of parallel points required for a target accuracy.
The study provides guarantees for diffusion-based models under log-concave data, offering best-known convergence rates.
problem Theoretical guarantees for convergence of diffusion-based generative models under log-concave data distributions.
method Assumption of strongly log-concave data distributions, Lipschitz continuous functions for score estimation, and novel auxiliary process.
result Best known upper bounds for Wasserstein-2 distance between Gaussian distribution and sampling algorithm.
Universal tester-learner for halfspaces over structured distributions.
problem Learning halfspaces over a wide class of structured distributions.
method Uses a fully polynomial tester-learner based on hypercontractivity and sum-of-squares (SOS) programs.
result Achieves error O ( o p t ) + ε O(\mathrm{opt}) + ε O ( opt ) + ε on any labeled distribution that the tester accepts. We consider the problem of sampling from a strongly log-concave density in R d \mathbb{R}^d R d , and prove a non-asymptotic upper bound on the mixing time of the Metropolis-adjusted Langevin algorithm (MALA). The method draws samples by simulating a Markov chain obtained from the discretization of an appropriate Langevin dif…
New method accelerates Bayesian imaging using Langevin sampling.
problem Bayesian inference in imaging inverse problems with convex geometry.
method Stochastic relaxed proximal-point iteration targeting posterior distribution.
result Accelerated convergence for κ κ κ -strongly log-concave targets. MALA mixes efficiently under smoothness and isoperimetry assumptions.
problem Sampling from target densities efficiently.
method Metropolis-Adjusted Langevin algorithm (MALA) with smoothness and isoperimetry assumptions.
result MALA mixes in $O\left(\frac{(LΥ)^{\frac12}}{ψ_μ^2} \log\left(\frac{1}ε
ight)
ight)$ iterations.
Sampling from log-concave distributions is a well researched problem that has many applications in statistics and machine learning. We study the distributions of the form p ∗ ∝ exp ( − f ( x ) ) p^{*}\propto\exp(-f(x)) p ∗ ∝ exp ( − f ( x )) , where f : R d → R f:\mathbb{R}^{d}\rightarrow\mathbb{R} f : R d → R has an L L L -Lipschitz gradient and is m m m -strongly convex. In our paper, we p…
Paper analyzes complexity of PSGLA for sampling log-concave distributions.
problem Sampling from log-concave distributions with composite potentials.
method Uses primal-dual interpretation and duality gap to analyze PSGLA complexity.
result Complexity of PSGLA is O ( 1 / ε 2 ) O(1/\varepsilon^2) O ( 1/ ε 2 ) for strongly convex potentials. Stein's method for measuring convergence to a continuous target distribution relies on an operator characterizing the target and Stein factor bounds on the solutions of an associated differential equation. While such operators and bounds are readily available for a diversity of univariate targets, few multivariate targ…
Poisson Midpoint Method improves Langevin Dynamics for diffusion models.
problem Slow convergence of LMC in diffusion models requiring many small steps.
method Poisson Midpoint Method approximates LMC with larger steps, proving quadratic speed up.
result Poisson Midpoint Method maintains quality of DDPM with fewer calls.
McDiarmid's inequality under dependence via approximate tensorization of entropy
problem Dependent versions of McDiarmid's inequality
method Approximate tensorization of entropy (ATE)
result Derives McDiarmid's inequality for non-isotropic Gaussian random vectors
Proves log-concavity of cluster algebra coefficients for type A n A_n A n .
problem Log-concavity of cluster algebra coefficients.
method Introduced atomic theta basis and proved log-concavity for type A n A_n A n . result Proved log-concavity of coefficients for cluster algebra variables of type A n A_n A n . Study improves sampling from non-log-concave distributions using Fisher information.
problem Sampling from non-log-concave distributions with high Fisher information guarantees.
method Proximal sampler with RGO implementation, leveraging log-concave sampling results.
result Improved complexity guarantee in relative Fisher information for non-log-concave sampling.
This paper improves low-precision sampling using SGHMC for deep learning models.
problem Enhancing training efficiency of deep neural networks with low-precision training.
method Investigates low-precision sampling via Stochastic Gradient Hamiltonian Monte Carlo (SGHMC) for both log-concave and non-log-concave distributions.
result Low-precision SGHMC achieves quadratic improvement in error compared to SGLD for non-log-concave distributions.
Establishes log-concavity estimates for convex domains' first Dirichlet eigenfunctions.
problem Quantifying the Hessian of log-concave eigenfunctions on convex domains.
method Analyzes log-concavity properties of the first Dirichlet eigenfunction on convex domains.
result Obtains quantitative estimates for the Hessian of log u \log u log u . This paper resolves the Langevin Algorithm's mixing time for log-concave distributions.
problem Resolving the mixing time of the Langevin Algorithm for log-concave sampling.
method Introducing Privacy Amplification by Iteration to analyze Rényi divergence and Optimal Transport smoothing.
result Optimal mixing bounds for the Langevin Algorithm in log-concave sampling settings.
New HMC framework reduces variance for sampling from log-concave distributions.
problem Efficient sampling from log-concave distributions with high precision.
method Unified formulation of biased and unbiased variance reduction methods for HMC.
result Unbiased and biased gradient estimators achieve different gradient complexities and accuracy.