thank you for sharing the great work! I notice that the beta and eta schedule (linear or exponential) in the code are different to the one proposed in the paper. Is this the case? if it is, does it mean the different schedules will lead to a similar result?
Hi,
thank you for sharing the great work! I notice that the beta and eta schedule (linear or exponential) in the code are different to the one proposed in the paper. Is this the case? if it is, does it mean the different schedules will lead to a similar result?
Thanks, Yufei