High Dimensional Discrete Integration by Hashing and Optimization
release_tmq4oe3pvrai5mynew5pqeldoi
by
Raj Kumar Maity, Arya Mazumdar, Soumyabrata Pal
2019
Abstract
Recently Ermon et al. (2013) pioneered a way to practically compute
approximations to large scale counting or discrete integration problems by
using random hashes. The hashes are used to reduce the counting problem into
many separate discrete optimization problems. The optimization problems then
can be solved by an NP-oracle such as commercial SAT solvers or integer linear
programming (ILP) solvers. In particular, Ermon et al. showed that if the
domain of integration is {0,1}^n then it is possible to obtain a solution
within a factor of 16 of the optimal (a 16-approximation) by this technique.
In many crucial counting tasks, such as computation of partition function of
ferromagnetic Potts model, the domain of integration is naturally {0,1,...,
q-1}^n, q>2, the hypergrid. The straightforward extension of Ermon et al.'s
method allows a q^2-approximation for this problem. For large values of q,
this is undesirable. In this paper, we show an improved technique to obtain an
approximation factor of 4+O(1/q^2) to this problem. We are able to achieve
this by using an idea of optimization over multiple bins of the hash functions,
that can be easily implemented by inequality constraints, or even in
unconstrained way. Also the burden on the NP-oracle is not increased by our
method (an ILP solver can still be used). Our method extends to the case when
the domain of integration is the symmetric group, and as a result we can obtain
a (4+o(1))-approximation of the permanent of a matrix. All these
results hold assuming the existence of an NP-oracle. We provide experimental
simulation results to support the theoretical guarantees of our algorithms,
including comparison to the popular Markov-Chain-Monte-Carlo (MCMC) methods.
In text/plain
format
Archived Files and Locations
application/pdf 1.1 MB
file_r2cieaiqevbx5fps5tcinpcidq
|
arxiv.org (repository) web.archive.org (webarchive) |
1806.11542v2
access all versions, variants, and formats of this works (eg, pre-prints)