Name
Abstract | ||
|---|---|---|
Many generative models have to combat missing modes. The conventional wisdom to this end is by reducing through training a statistical distance (such as f-divergence) between the generated distribution and provided data distribution. But this is more of a heuristic than a guarantee. The statistical distance measures a global, but not local, similarity between two distributions. Even if it is small, it does not imply a plausible mode coverage. Rethinking this problem from a game-theoretic perspective, we show that a complete mode coverage is firmly attainable. If a generative model can approximate a data distribution moderately well under a global statistical distance measure, then we will be able to find a mixture of generators that collectively covers every data point and thus every mode, with a lower-bounded generation probability. Constructing the generator mixture has a connection to the multiplicative weights update rule, upon which we propose our algorithm. We prove that our algorithm guarantees complete mode coverage. And our experiments on real and synthetic datasets confirm better mode coverage over recent approaches, ones that also use generator mixtures but rely on global statistical distances. |
Year | Venue | Keywords |
|---|---|---|
2019 | ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS 32 (NIPS 2019) | generative model,conventional wisdom |
Field | DocType | Volume |
Mathematical optimization,Computer science,Artificial intelligence,Generative grammar,Pointwise | Conference | 32 |
ISSN | Citations | PageRank |
1049-5258 | 0 | 0.34 |
References | Authors | |
0 | 5 | |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Peilin Zhong | 1 | 99 | 10.36 |
| Yuchen Mo | 2 | 0 | 0.68 |
| Chang Xiao | 3 | 1 | 1.36 |
| Pengyu Chen | 4 | 0 | 1.01 |
| Changxi Zheng | 5 | 571 | 37.17 |