A note on concentration of submodular functions

نویسنده

  • Jan Vondrák
چکیده

We survey a few concentration inequalities for submodular and fractionally subadditive functions of independent random variables, implied by the entropy method for self-bounding functions. The power of these concentration bounds is that they are dimension-free, in particular implying standard deviation O( √ E[f ]) rather than O( √ n) which can be obtained for any 1Lipschitz function of n variables.

برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

منابع مشابه

Some Results about the Contractions and the Pendant Pairs of a Submodular System

Submodularity is an important  property of set functions with deep theoretical results  and various  applications. Submodular systems appear in many applicable area, for example machine learning, economics, computer vision, social science, game theory and combinatorial optimization.  Nowadays submodular functions optimization has been attracted by many researchers.  Pendant pairs of a symmetric...

متن کامل

A Note on Submodular Functions on Distributive Lattices

A NOTE ON SUBMODULAR FUNCTIONS ON DISTRIBUTIVE LATTICES Satoru Fujishige University of Tsukuba Nobuaki Tomizawa Niigata University (Received July 15, 1982; Rllvised June 14, 1983) Let D be a distributive lattice formed by subsets of a finite set E with 1/>, E E D and let R be the set of reals. Also let f be a submodular function from D into R with f(l/» = O. We determine the set of extreme poin...

متن کامل

A note on the budgeted maximization of submodular functions

Many set functions F in combinatorial optimization satisfy the diminishing returns property F{A U X) — F(A) > F(A' U X) — F(A') for A C A!. Such functions are called submodular. A result from Nemhauser etal. states that the problem of selecting ^-element subsets maximizing a nondecreasing submodular function can be approximated with a constant factor (1 — 1/e) performance guarantee. Khuller eta...

متن کامل

A Reduction for Optimizing Lattice Submodular Functions with Diminishing Returns

A function f : ZE+ → R+ is DR-submodular if it satisfies f(x+χi)−f(x) ≥ f(y+χi)−f(y) for all x ≤ y, i ∈ E. Recently, the problem of maximizing a DR-submodular function f : ZE+ → R+ subject to a budget constraint ‖x‖1 ≤ B as well as additional constraints has received significant attention [6, 7, 5, 8]. In this note, we give a generic reduction from the DR-submodular setting to the submodular se...

متن کامل

A note on the Minimum Norm Point algorithm

We present a provably more efficient implementation of the Minimum Norm Point Algorithm conceived by Fujishige than the one presented in [FUJI06]. The algorithm solves the minimization problem for a class of functions known as submodular. Many important functions, such as minimum cut in the graph, have the so called submodular property [FUJI82]. It is known that the problem can also be efficien...

متن کامل

ذخیره در منابع من


  با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید

برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

عنوان ژورنال:
  • CoRR

دوره abs/1005.2791  شماره 

صفحات  -

تاریخ انتشار 2010