Loading...
Please wait, while we are loading the content...
Similar Documents
D S ] 2 9 O ct 2 01 8 Robust Learning of Fixed-Structure Bayesian Networks
| Content Provider | Semantic Scholar |
|---|---|
| Author | Cheng, Yu |
| Copyright Year | 2018 |
| Abstract | We investigate the problem of learning Bayesian networks in a robust model where an ǫfraction of the samples are adversarially corrupted. In this work, we study the fully observable discrete case where the structure of the network is given. Even in this basic setting, previous learning algorithms either run in exponential time or lose dimension-dependent factors in their error guarantees. We provide the first computationally efficient robust learning algorithm for this problem with dimension-independent error guarantees. Our algorithm has near-optimal sample complexity, runs in polynomial time, and achieves error that scales nearly-linearly with the fraction of adversarially corrupted samples. Finally, we show on both synthetic and semisynthetic data that our algorithm performs well in practice. |
| File Format | PDF HTM / HTML |
| Alternate Webpage(s) | http://arxiv-export-lb.library.cornell.edu/pdf/1606.07384 |
| Alternate Webpage(s) | https://www.cse.wustl.edu/~bjuba/cse519t/f19/papers/Cheng18-full.pdf |
| Language | English |
| Access Restriction | Open |
| Content Type | Text |
| Resource Type | Article |
