Bringing Continual Learning into Enterprises — Samuel Denton, Applied Compute
Applied Compute is bringing continual learning to enterprises via a distillation spectrum from offline to online
“this is sort of the holy grail of continual learning where I have a model that's serving production traffic, it does a rollout, it creates a trace, we figure out how to learn from that trace, we update the model”
Samuel Denton of Applied Compute outlines a distillation spectrum ranging from offline batch learning on production traces to a fully online unified inference-training loop, framing the latter as the holy grail of continual learning. The talk focuses on practical enterprise deployment of self-distillation techniques. While technically substantive, it represents practitioner-level implementation work rather than a novel research finding or major industry announcement.