Modified log-Sobolev inequalities for strongly log-concave distributions
نویسندگان
چکیده
We show that the modified log-Sobolev constant for a natural Markov chain which converges to an $r$-homogeneous strongly log-concave distribution is at least $1/r$. Applications include sharp mixing time bound bases-exchange walk matroids, and concentration Lipschitz functions over these distributions.
منابع مشابه
Modified Log-sobolev Inequalities and Isoperimetry
We find sufficient conditions for a probability measure μ to satisfy an inequality of the type ∫ Rd fF ( f ∫ Rd f 2 dμ ) dμ ≤ C ∫ Rd f2c∗ ( |∇f | |f | ) dμ + B ∫ Rd f dμ, where F is concave and c (a cost function) is convex. We show that under broad assumptions on c and F the above inequality holds if for some δ > 0 and ε > 0 one has ∫ ε 0 Φ ( δc [ tF ( 1t ) Iμ(t) ]) dt <∞, where Iμ is the isop...
متن کاملLearning Multivariate Log-concave Distributions
We study the problem of estimating multivariate log-concave probability density functions. We prove the first sample complexity upper bound for learning log-concave densities on Rd, for all d ≥ 1. Prior to our work, no upper bound on the sample complexity of this learning problem was known for the case of d > 3. In more detail, we give an estimator that, for any d ≥ 1 and ǫ > 0, draws Õd ( (1/ǫ...
متن کاملClustering with mixtures of log-concave distributions
The EM algorithm is a popular tool for clustering observations via a parametric mixture model. Two disadvantages of this approach are that its success depends on the appropriateness of the assumed parametric model, and that each model requires a different implementation of the EM algorithm based on model-specific theoretical derivations. We show how this algorithm can be extended to work with t...
متن کاملInference and Modeling with Log-concave Distributions
Log-concave distributions are an attractive choice for modeling and inference, for several reasons: The class of log-concave distributions contains most of the commonly used parametric distributions and thus is a rich and flexible nonparametric class of distributions. Further, the MLE exists and can be computed with readily available algorithms. Thus, no tuning parameter, such as a bandwidth, i...
متن کاملMixed f - divergence and inequalities for log concave functions ∗
Mixed f -divergences, a concept from information theory and statistics, measure the difference between multiple pairs of distributions. We introduce them for log concave functions and establish some of their properties. Among them are affine invariant vector entropy inequalities, like new Alexandrov-Fenchel type inequalities and an affine isoperimetric inequality for the vector form of the Kull...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
ژورنال
عنوان ژورنال: Annals of Probability
سال: 2021
ISSN: ['0091-1798', '2168-894X']
DOI: https://doi.org/10.1214/20-aop1453