Timezone: »

Instance Based Approximations to Profile Maximum Likelihood
Nima Anari · Moses Charikar · Kirankumar Shiragur · Aaron Sidford

Thu Dec 10 09:00 AM -- 11:00 AM (PST) @ Poster Session 5 #518

In this paper we provide a new efficient algorithm for approximately computing the profile maximum likelihood (PML) distribution, a prominent quantity in symmetric property estimation. We provide an algorithm which matches the previous best known efficient algorithms for computing approximate PML distributions and improves when the number of distinct observed frequencies in the given instance is small. We achieve this result by exploiting new sparsity structure in approximate PML distributions and providing a new matrix rounding algorithm, of independent interest. Leveraging this result, we obtain the first provable computationally efficient implementation of PseudoPML, a general framework for estimating a broad class of symmetric properties. Additionally, we obtain efficient PML-based estimators for distributions with small profile entropy, a natural instance-based complexity measure. Further, we provide a simpler and more practical PseudoPML implementation that matches the best-known theoretical guarantees of such an estimator and evaluate this method empirically.

Author Information

Nima Anari (Stanford)
Moses Charikar (Stanford University)
Kirankumar Shiragur (Stanford University)
Aaron Sidford (Stanford)

More from the Same Authors