R.I.P.
👻
Ghosted
Modified log-Sobolev inequalities for strongly log-concave distributions
March 14, 2019 · Declared Dead · 🏛 IEEE Annual Symposium on Foundations of Computer Science
"No code URL or promise found in abstract"
Evidence collected by the PWNC Scanner
Authors
Mary Cryan, Heng Guo, Giorgos Mousa
arXiv ID
1903.06081
Category
math.PR
Cross-listed
cs.DS,
math.CO
Citations
74
Venue
IEEE Annual Symposium on Foundations of Computer Science
Last Checked
3 months ago
Abstract
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 a sharp mixing time bound for the bases-exchange walk for matroids, and a concentration bound for Lipschitz functions over these distributions.
Community Contributions
Found the code? Know the venue? Think something is wrong? Let us know!
📜 Similar Papers
In the same crypt — math.PR
R.I.P.
👻
Ghosted
An Introduction to Matrix Concentration Inequalities
R.I.P.
👻
Ghosted
Non-backtracking spectrum of random graphs: community detection and non-regular Ramanujan graphs
R.I.P.
👻
Ghosted
Convergence of the Deep BSDE Method for Coupled FBSDEs
R.I.P.
👻
Ghosted
A Random Matrix Approach to Neural Networks
R.I.P.
👻
Ghosted
Concentration and regularization of random graphs
Died the same way — 👻 Ghosted
R.I.P.
👻
Ghosted
Language Models are Few-Shot Learners
R.I.P.
👻
Ghosted
PyTorch: An Imperative Style, High-Performance Deep Learning Library
R.I.P.
👻
Ghosted
XGBoost: A Scalable Tree Boosting System
R.I.P.
👻
Ghosted