Mistake-bounded online learning with operation caps
By: Jesse Geneson, Meien Li, Linus Tang
Potential Business Impact:
Teaches computers to learn with fewer steps.
We investigate the mistake-bound model of online learning with caps on the number of arithmetic operations per round. We prove general bounds on the minimum number of arithmetic operations per round that are necessary to learn an arbitrary family of functions with finitely many mistakes. We solve a problem on agnostic mistake-bounded online learning with bandit feedback from (Filmus et al, 2024) and (Geneson \& Tang, 2024). We also extend this result to the setting of operation caps.
Similar Papers
Optimal Mistake Bounds for Transductive Online Learning
Machine Learning (CS)
Lets computers learn more with unlabeled data.
Online Learning of Neural Networks
Machine Learning (Stat)
Teaches computers to learn faster with fewer mistakes.
Capacity-Constrained Online Learning with Delays: Scheduling Frameworks and Regret Trade-offs
Machine Learning (CS)
Makes computers learn faster with delayed information.