AI Paper Atlas

Research map / Bandits and online learning / Online convex optimization and games

Online Forecasting of Total-Variation-bounded Sequences

Dheeraj Baby, Yu-Xiang Wang

NeurIPS 2019 · Bandits and online learning › Online convex optimization and games · approach: Parameter-free non-stationary online learning · 12 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
Replace the proposed adaptive nonlinear policy with a linear forecasterTV(C_n) forecasting · TV(C_n) forecastingdynamic regret rate: n^{1/3} versus n^{1/2}Hurt
Use Arrows without tuning to the specific radius of the function classArrows · Sobolev forecastingforecasting rate: n^{2/3}[C_n']^{2/3}\sigma^{4/3} + [C_n']^2 + \sigma^2Improved
Use Arrows without tuning to the specific radius of the function classArrows · Holder forecastingforecasting rate: nL_n^{2/3}\sigma^{4/3} + nL_n^2 + \sigma^2Improved
Make forecasts online rather than use smoothing with access to all observationsTV(C_n) prediction · TV(C_n) forecasting versus smoothingminimax cumulative error: C_n^2Hurt

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy