NF-BO is a latent Bayesian optimization framework that uses normalizing flows for a one-to-one input-latent mapping and token-level adaptive sampling, outperforming prior LBO methods on Guacamol and PMO benchmarks.
Figures 8, 9, and 10 display the results for the (100, 500), (10,000, 10,000), and (10,000, 70,000) oracle settings, respectively
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Latent Bayesian Optimization via Autoregressive Normalizing Flows
NF-BO is a latent Bayesian optimization framework that uses normalizing flows for a one-to-one input-latent mapping and token-level adaptive sampling, outperforming prior LBO methods on Guacamol and PMO benchmarks.