|
|
|
|
| LEADER |
01436 am a22001693u 4500 |
| 001 |
129554 |
| 042 |
|
|
|a dc
|
| 100 |
1 |
0 |
|a Indyk, Piotr
|e author
|
| 100 |
1 |
0 |
|a Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science
|e contributor
|
| 245 |
0 |
0 |
|a Estimating entropy of distributions in constant space
|
| 260 |
|
|
|b Neural Information Processing Systems Foundation,
|c 2021-01-25T19:53:49Z.
|
| 856 |
|
|
|z Get fulltext
|u https://hdl.handle.net/1721.1/129554
|
| 520 |
|
|
|a We consider the task of estimating the entropy of k-ary distributions from samples in the streaming model, where space is limited. Our main contribution is an algorithm that requires O ( klog(1"3/")2 ) samples and a constant O(1) memory words of space and outputs a ±" estimate of H(p). Without space limitations, the sample complexity has been established as S(k, ") = T ( "logkk + log"22 k 0, which is sub-linear in the domain size k, and the current algorithms that achieve optimal sample complexity also require nearly-linear space in k. Our algorithm partitions [0, 1] into intervals and estimates the entropy contribution of probability values in each interval. The intervals are designed to trade off the bias and variance of these estimates.
|
| 520 |
|
|
|a National Science Foundation (U.S.). Computing and Communication Foundation (Grant 657471)
|
| 546 |
|
|
|a en
|
| 655 |
7 |
|
|a Article
|
| 773 |
|
|
|t Advances in Neural Information Processing Systems
|
