Proposes a control-theoretic pipeline using Gauss-Markov and instrumental-variable estimators to reconstruct and forecast latent time-varying parameters from noisy gradients in strongly convex online optimization, along with a bound on expected tracking error.
Dall’Anese, A
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
math.OC 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Online Optimization with Unknown Time-Varying Parameters from Noisy Gradient Measurements
Proposes a control-theoretic pipeline using Gauss-Markov and instrumental-variable estimators to reconstruct and forecast latent time-varying parameters from noisy gradients in strongly convex online optimization, along with a bound on expected tracking error.