A Preliminary
–Neural Information Processing Systems
We first introduce necessary notations as follows. "LB" is lower bound while "UB" is upper bound. Quantity µ is the PL constant. These rates are derived under the strongly-convex assumption, not the general PL condition. This rate is achieved by utilizing increasing (non-constant) mini-batch sizes.
Neural Information Processing Systems
Nov-17-2025, 09:00:54 GMT
- Technology: