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.
Relative loss bound s for on-line density estimation with the exponential family of distributions
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.