Predictive hints from any stabilizing Luenberger observer make hint residuals uniformly bounded in online least squares, yielding logarithmic regret for nonstochastic prediction despite unbounded trajectories in marginally stable systems.
Model-free online learnin g for the Kalman filter: Forgetting factor and logarithmic regret
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Online Nonstochastic Prediction: Logarithmic Regret via Predictive Online Least Squares
Predictive hints from any stabilizing Luenberger observer make hint residuals uniformly bounded in online least squares, yielding logarithmic regret for nonstochastic prediction despite unbounded trajectories in marginally stable systems.