The Complexity of Statistical Algorithms

Details The Complexity of Statistical Algorithms The Complexity of Statistical Algorithms

2012-01-05

arxiv.org/abs/1201.1214v1

Computer Science

Computational Complexity

Scientific paper

We develop a framework for studying optimization problems over distributions. In the worst case these problems are typically NP-hard, even to approximate, and are usually addressed in practice by a range of heuristics. To understand the effectiveness of such approaches, we define a class of algorithms, called statistical algorithms, that captures many natural algorithms, e.g. local search, MCMC, and simulated annealing. We show that for specific optimization problems over distributions, namely, for variants of MAX-XOR-SAT, k-clique, and moment maximization, the complexity of any statistical algorithm grows exponentially in their input parameters. Our techniques are inspired by (and generalize) the statistical query model in learning theory, and in parallel to that concept, we can prove lower bounds on statistical algorithms for optimization problems over distributions using a single parameter that we call statistical dimension. Although this does not fully rule out efficient algorithms for such problems, it indicates the limitations of known heuristics.

Affiliated with

Also associated with

No associations

Rating

The Complexity of Statistical Algorithms does not yet have a rating. At this time, there are no reviews or comments for this scientific paper.

If you have personal experience with The Complexity of Statistical Algorithms, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and The Complexity of Statistical Algorithms will most certainly appreciate the feedback.

Rate now

Comments { 0 }

Profile ID: LFWR-SCP-O-610225