Oracle-Efficient and Parameter-Free Agnostic Smoothed Online Learning
A parameter-free Follow-The-Perturbed-Leader method gets near-optimal agnostic smoothed online regret without knowing the base measure.
1 stories, newest first · one card per story
A parameter-free Follow-The-Perturbed-Leader method gets near-optimal agnostic smoothed online regret without knowing the base measure.
Today 485 readers · 546 views · 176 reads · all time 187K views