Ensuring complete marginal bit coverage in initial data for one-hot encoded FMQA improves mean optimization performance on wing-shape benchmarks with 17 and 32 variables.
In FMQA, an FM is trained on observed input-output data to approxi- mate the BB function
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Improving FMQA via Initial Training Data Design Considering Marginal Bit Coverage in One-Hot Encoding
Ensuring complete marginal bit coverage in initial data for one-hot encoded FMQA improves mean optimization performance on wing-shape benchmarks with 17 and 32 variables.