Open nabenabe0928 opened 1 year ago
Hi
The implementation details were verified and cross-checked by the then official
implementation of HyperBand as seen here.
Therefore, in our experiments, the comparison of DEHB with HB and BOHB is much fairer as one can see that during the first HB iteration, all 3 algorithms perform similarly.
The DEHB paper says that each SH bracket samples $n = \lceil \frac{s{\max} + 1}{s + 1} \eta^s \rceil$ configurations; however, this line samples $n = \lfloor\lfloor \frac{s{\max} + 1}{s + 1} \rfloor \eta^s\rfloor$ configurations. In reality, this line should be:
Note that
self.max_SH_iter
is $s_{\max} + 1$.