LTSPDProject reference: 630837
Funded under :
Learning and Testing Structured Probability Distributions
Total cost:EUR 100 000
EU contribution:EUR 100 000
Coordinated in:United Kingdom
Call for proposal:FP7-PEOPLE-2013-CIGSee other projects for this call
Funding scheme:MC-CIG - Support for training and career development of researcher (CIG)
"The research topic of the current proposal lies within the area of Algorithms and Complexity.
The goal of this proposal is to advance a research program of developing
computationally efficient algorithms for learning and testing
a wide range of natural and important classes of probability distributions.
We live in an era of “big data,” where the amount of data that can be brought to bear
on questions of biology, climate, economics, etc, is vast and expanding rapidly.
Much of this raw data frequently consists of example points without corresponding labels.
The challenge of how to make sense of this unlabeled data has immediate relevance
and has rapidly become a bottleneck in scientific understanding across many disciplines.
An important class of big data is most naturally modeled as samples
from a probability distribution over a very large domain.
This prompts the basic question:
Given samples from some unknown distribution, what can we infer?
While this question has been studied for several decades
by various different communities of researchers,
both the number of samples and running time required for such estimation tasks
are not yet well understood, even for some surprisingly simple types of discrete distributions.
In this project we will develop computationally efficient algorithms
for learning and testing various classes of discrete distributions over very large domains.
Specific problems we will address include:
(1) Developing efficient algorithms to learn and test probability distributions that satisfy various
natural types of ""shape restrictions"" on the underlying probability density function.
(2) Developing efficient algorithms for learning and testing complex distributions that result
from the aggregation of many independent simple sources of randomness.
We believe that highly efficient algorithms for these estimation tasks
may play an important role for the next generation of large-scale machine learning applications."
EU contribution: EUR 100 000
OLD COLLEGE, SOUTH BRIDGE
EH8 9YL EDINBURGH
Tel.: +44 131 650 59024
Fax: +44 131 651 4028