Santosh Vempala Georgia Tech A really old p roblem Given set K in ndimensional space estimate its volume Eg Pyramids wine barrels Polytopes Intersection of a polytope with ellipsoids ID: 273509
Download Presentation The PPT/PDF document "Sampling and Volume Computation in High ..." is the property of its rightful owner. Permission is granted to download and print the materials on this web site for personal, non-commercial use only, and to display it on your personal computer provided you do not modify the materials and that you retain all copyright notices contained in the materials. By downloading content from our website, you accept the terms of this agreement.
Slide1
Sampling and Volume Computation in High Dimension
Santosh
Vempala
, Georgia TechSlide2
A really old problem
Given set K in n-dimensional space, estimate its volume.
E.g.,
Pyramids, wine barrels, …
Polytopes
Intersection of a polytope with ellipsoid(s)
Section of the
semidefinite
cone
Fundamental,
computational
: how much?Slide3
Computational model
Well-guaranteed Membership oracle:
Compact set
K is given by
a membership oracle: answers YES/NO to “
a point Numbers r, R s.t. Well-guaranteed Function oracleAn oracle that returns for any A point with Numbers r, R s.t. and
Slide4
High-dimensional problems
Input:
A set of points S in n-dimensional space
or a distribution in
A function f that maps points to real values (could be the indicator of a set) Slide5
High-dimensional problems
What is the
complexity
of computational problems
as the dimension grows
?Dimension = number of variablesTypically, size of input is a function of the dimension.Slide6
Sampling and Integration
Numerous applications in diverse areas: statistics, networking, biology, computer vision, privacy, operations research etc.
This tutorial: mathematical and algorithmic foundations of sampling and integration.Slide7
Problem 1: Optimization
Input: function f:
specified
by an oracle,
point x, error parameter . Output: point y such that Slide8
Problem 2: Integration
Input: function f:
specified
by an oracle,
point
x, error parameter . Output: number A such that: Slide9
Problem 3: Sampling
Input: function f:
specified
by an oracle,
point x, error parameter . Output: A point y from a distribution within distance of distribution with density proportional to f. Slide10
Problem 4: Rounding
Input: function f:
specified
by an oracle,
point
x, error parameter . Output: An affine transformation that approximately “rounds” f, between two balls. Slide11
Problem 5: Learning
Input:
i.i.d
. points
with labels
from an unknown distribution, error parameter .Output: A rule to correctly label 1- of the input distribution. Slide12
High-dimensional problems
Integration (volume
)
Optimization
Learning
Rounding SamplingAll intractable in general, even to approximate.Slide13
Structure
Q. What
structure
makes
high-dimensional problems computationally tractable? (i.e., solvable with polynomial complexity)Convexity and its extensions appear to be the frontier of polynomial-time solvability.Slide14
Tutorial outline
Part 1. Intro to high dimension and convexity
Volume distribution,
logconcavity
Ellipsoids
Lower boundsPart 2. AlgorithmsRoundingVolume/IntegrationOptimizationSamplingPart 3. ProbabilityMarkov chainsConductanceMixing of ball walkMixing of hit-and-runPart 4. GeometryIsoperimetryConcentrationLocalization and applicationsOpen problemsSlide15
An o..old p
roblem
Given a measurable, compact set K in n-dimensional space and
, find a number A such that:
K is given by a well-guaranteed membershi
p oracle. Slide16
Volume: first attempt
Divide and conquer:
Difficulty: number of parts grows exponentially in n.Slide17
Volume distribution
Volume(unit cube) = 1
Volume(unit ball)
drops exponentially with n.
For any central hyperplane, most of the mass of the unit ball is within distance . Section volume decays as at distance from the origin. Slide18
Volume distribution
Volume(unit cube) = 1
Volume(unit ball)
drops exponentially with n.
For any central hyperplane, most of the mass of the unit ball is within distance .Most of the volume is near the boundary: So, “Everything interesting for a convex body happens near its boundary” --- Imre Bárány. Slide19
Volume distribution
A,B
sets
in
, their
Minkowski sum is:For a convex body, the hyperplane section at contains .What is the volume distribution? Slide20
Brunn-Minkowski inequality
Thm
.
A, B compact sets in
Suffices to prove by taking the sets to be
Slide21
Brunn-Minkowski inequality
Thm. A, B: compact sets in
Proof. First take A, B to be cuboids, i.e.,
=
.
Slide22
Brunn-Minkowski inequality
Thm. A, B: compact sets in
T
ake A,B to be finite unions of disjoint cuboids:
A =
and B = . Induction.There exists an axis-parallel hyperplane s.t. at least one complete cuboid of A is on either side. Partition into Translate B s.t.
(induction)
Approximate to arbitrary accuracy by a finite union of cuboids.
Slide23
Logconcave functions
i.e., f is nonnegative and its logarithm is concave.
Slide24
Logconcave functions
Examples:
Indicator functions of convex sets are
logconcave
Gaussian density function,
exponential functionLevel sets, are convex.Many other useful geometric properties Slide25
Properties of logconcave functions
For two
logconcave
functions f and g
Their sum might not be
logconcaveBut their product h(x) = f(x)g(x) is logconcave And so is their minimum h(x) = min f(x), g(x).Slide26
Prekopa-Leindler inequality
Prekopa-Leindler
:
t
hen
Functional version of [B-M], equivalent to it. Slide27
Properties of logconcave functions
Convolution
is
logconcave
E.g., any marginal:This follows from Prekopa-Leindler. Slide28
Volume: second attempt: Ellipsoids
Ellipsoid #1: John
e
llipsoid of a convex body K:
E = maximum volume ellipsoid contained in K
.Thm. For any convex body K, the John ellipsoid satisfies For any centrally-symmetric K, . Slide29
Approximate John ellipsoid
Variant of the Ellipsoid algorithm:
suppose current center is
and axes are
Check if
. If so, output current ellipsoid.If not, then intersect E with halfspace H not containing and continue algorithm (replace E with min volume ellipsoid containing ).Thm. Algorithm outputs E satisfying Slide30
Volume via (approximate) John ellipsoid
Using the Ellipsoid algorithm, in
polytime
Then
Polytime
, exponential approximation Slide31
Ellipsoid #2: Inertial ellipsoid
For a convex body K,
matrix of inertia:
Inertial ellipsoid:
Thm (KLS95). Also a factor sandwiching, but a different ellipsoid. Shown earlier up to constants by Milman-Pajor. Slide32
Isotropic position
For any distribution with bounded second moments, there is an affine transformation to make it isotropic.
Applying this to a convex body K:
Thus K “looks like a ball” up to second moments.
How close is it really to a ball?
K lies between two balls with radii within a factor of n. Slide33
Volume via ellipsoidal approximation
The Inertial ellipsoid can be approximated to within any constant factor (we’ll see how)
Therefore:
Polytime
algorithm, approximation Can we do better? Slide34
Ellipsoid #3: Milman Ellipsoid
For two compact sets
= #translates of
needed to cover
Thm
(Milman). For any convex body K, there is an ellipsoid E s.t., Many important consequences in convex geometry.Thm (Dadush-V.). Deterministc complexity of computing a Milman ellipsoid is time, approximation.Can we do better?! Slide35
Complexity of Volume Estimation
Thm
[E86, BF87]. For any deterministic algorithm that uses at most
membership
calls to the oracle for a convex body K and computes two numbers A and B such that
, there is some convex body for which the ratio B/A is at leastwhere c is an absolute constant.Thm [DF88]. Computing the volume of an explicit polytope is #P-hard, even for a totally unimodular matrix A and rational b. Slide36
Deterministic Volume Estimation
Thm
[
BF].
For deterministic algorithms:
# oracle calls approximation factor Thm [Dadush-V.13]. Matching approximation factor of in time Slide37
Lower bound for volume estimation
[
Elekes
]
Membership oracle answers “YES” for points in unit ball, “No” for points outside.
After m queries, volume of K is between volume of convex hull and volume of unit ball. Lemma. Need exponentially many queries! Slide38
Lower bound for volume estimation
Lemma.
Proof. Let
ball of radius
around
Claim 1. Claim 2. .
is acute, i.e.,
and
are on the same side of orthogonal hyperplane through y. Hence,
.
Slide39
Randomized Volume/Integration
[DFK89].
Polytime
randomized
algorithm that estimates volume to within relative error with probability at least in time poly(n, ). [Applegate-K91]. Polytime randomized algorithm to estimate integral of any (Lipshitz) logconcave function. Slide40
Volume: third attempt: Sampling
Pick random samples from ball/cube containing K.
Compute fraction
c
of sample in K.
Output c.vol(outer ball).Need too many samples!Slide41
Volume via Sampling [DFK89]
Let
Estimate
each ratio with random samples
.
(Markov Chain Monte-Carlo method)
Slide42
Volume via Sampling
Claim.
Slide43
Variance of estimate [DF91]
using k samples in each phase.
So
samples in each phase suffice.
Total number of samples
But, how to sample?
Slide44
Sampling
Generate a point
uniform a compact set S
with density proportional to a function f
.We will discuss this in detail shortly!Slide45
Sampling
Input: function f:
specified
by an oracle,
point x, error parameter . Output: A point y from a distribution within distance of distribution with density proportional to f. Slide46
Algorithmic applications
Given a
blackbox
for sampling
logconcave
densities, we get efficient algorithms for: RoundingConvex OptimizationVolume Computation/Integrationsome Learning problemsSlide47
Rounding via Sampling
Sample
m random points from K;
Compute
sample mean
and sample covariance matrix .Output B(K-z) is nearly isotropic.Thm. C().n random points suffice to get . [Adamczak et al; improving on Bourgain, Rudelson] I.e., for any unit vector v, Slide48
Complexity of Sampling
Thm
.
[KLS97] For a convex body, the
ball walk with an M-warm start reaches an (independent) nearly random point in poly(n,
R, M) steps.Thm. [LV03]. Same holds for arbitary logconcave density functions. Complexity is .Isotropic transformation makes R=O(); M can be kept at O(1).KLS’97 volume algorithm: Slide49
Progress on Volume Computation
Power
New aspects
Dyer-Frieze-Kannan 89 23 everythingLovász-Simonovits 90 16 localization Applegate-K 90 10 logconcave integrationL 90 10 ball walkDF 91 8 error analysisLS 93 7 multiple improvementsKLS 97 5 speedy walk, isotropyLV 03,04 4 annealing, wt. isoper.LV 06 4 integration, local analysisCousins-V. 13, 14 3 Gaussian coolingSlide50
Simulated Annealing
[LV03, Kalai-V.04]
To estimate
consider a sequence
with
being easy, e.g., constant function over ball. Then, Each ratio can be estimated by sampling:Sample X with density proportional to Compute
Then,
.
.
Slide51
Annealing [LV06]
Define:
phases
The final estimate could be
, so each ratio could be
or higher. How can we estimate it with a few samples?!
Slide52
Annealing [LV03, 06]
Lemma
.
Although expectation of Y can be large (exponential even), we need only a few samples to estimate it!Lo-Ve algorithm:
Slide53
Variance of ratio estimator
Let
Then,
.
(would be at most 1, if F was
logconcave
…)
Slide54
Variance of ratio estimator
Lemma. For any logconcave f and a >0, the function
is also
logconcave
.
So is logconcave and Therefore:
.
f
or
.
Slide55
Optimization via Annealing
For
Sample with density prop. to
.
Output X with
[Abernathy-
Hazan
15
]:
Interior point with entropic barrier
[
Bubek-Eldan
]
is equivalent to simulated annealing with exponential functions.
Slide56
Annealing
Integration:
Sample from
.
Estimate Output
Optimization
:
Sample
from
.
Output X with max f(X).
Slide57
Progress on Volume Computation
Power
New aspects
Dyer-Frieze-Kannan 89 23 everythingLovász-Simonovits 90 16 localization Applegate-K 90 10 logconcave integrationL 90 10 ball walkDF 91 8 error analysisLS 93 7 multiple improvementsKLS 97 5 speedy walk, isotropyLV 03,04 4 annealing, wt. isoper.LV 06 4 integration, local analysisCousins-V. 13, 14 3 Gaussian coolingSlide58
A MATLAB program
[
Cousins-V.13
]
Matlab
implementation of sampling and integration“volume computation matlab exchange”http://www.cc.gatech.edu/~bcousins/volume.htmlPlease download from MATLAB Exchange if you’d like to try it.Slide59
Rotated cubesSlide60
How to Sample?
Ball walk:
At
x,
-pick random y from -if y is in K, go to yHit-and-Run: At x, -pick a random chord L through x -go to a random point y on L