Author

B. Nia

View on Semantic Scholar

1 paper indexed here

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

#artificial intelligence Preprint Mar 2026

Mixture-Greedy for Online Generative Model Selection: Is UCB Necessary in Diversity-Aware Multi-Armed Bandits?

These results suggest that in diversity-aware multi-armed bandits, e.g., for generative model selection, exploration can arise intrinsically from the objective's geometry, particularly for widely used metrics such as FID and Vendi where tight confidence bounds are difficult to construct.

B. Nia, F. Farnia · 2 citations