no code implementations • 27 Feb 2024 • Siddhartha Banerjee, Alankrita Bhatt, Christina Lee Yu
We devise an online learning algorithm -- titled Switching via Monotone Adapted Regret Traces (SMART) -- that adapts to the data and achieves regret that is instance optimal, i. e., simultaneously competitive on every input sequence compared to the performance of the follow-the-leader (FTL) policy and the worst case guarantee of any other input policy.
1 code implementation • 4 Feb 2022 • J. Jon Ryu, Alankrita Bhatt, Young-Han Kim
A class of parameter-free online linear optimization algorithms is proposed that harnesses the structure of an adversarial sequence by adapting to some side information.