A size-free CLT for poisson multinomials and its applications
An (n,k)-Poisson Multinomial Distribution (PMD) is the distribution of the sum of n independent random vectors supported on the set Bk={e1,...,ek} of standard basis vectors in ℝk. We show that any (n,k)-PMD is poly(k/σ)-close in total variation distance to the (appropriately discretized) multi-dimen...
Main Authors: | De, Anindya (Author), Kamath, Gautam (Author), Daskalakis, Konstantinos (Contributor), Kamath, Gautam Chetan (Contributor), Tzamos, Christos (Contributor) |
---|---|
Other Authors: | Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science (Contributor) |
Format: | Article |
Language: | English |
Published: |
Association for Computing Machinery,
2017-07-25T17:00:43Z.
|
Subjects: | |
Online Access: | Get fulltext |
Similar Items
-
On the Structure, Covering, and Learning of Poisson Multinomial Distributions
by: Daskalakis, Konstantinos, et al.
Published: (2017) -
Optimal testing for properties of distributions
by: Acharya, Jayadev, et al.
Published: (2017) -
Surveillance of Poisson and Multinomial Processes
by: Ryan, Anne Garrett
Published: (2014) -
Modern challenges in distribution testing
by: Kamath, Gautam (Gautam Chetan)
Published: (2019) -
On Learning and Covering Structured Distributions
by: Kamath, Gautam (Gautam Chetan)
Published: (2015)