Title :
A note on a Lyapunov argument for stochastic gradient methods in the presence of noise
Author :
Sayed, Ali H. ; Kokotovic, Petar V.
Author_Institution :
Dept. of Electr. & Comput. Eng., California Univ., Santa Barbara, CA, USA
Abstract :
The authors employ energy-based arguments to establish a robustness and a convergence result for a gradient-descent adaptive law in the presence of both noisy measurements and uncertainty in the initial guess
Keywords :
Lyapunov methods; convergence; estimation theory; filtering theory; noise; robust control; Lyapunov argument; convergence; energy-based arguments; gradient-descent adaptive law; noise; noisy measurements; robustness; stochastic gradient methods; uncertainty; Convergence; Electric variables measurement; Energy measurement; Estimation error; Gradient methods; Lyapunov method; Measurement uncertainty; Noise measurement; Noise robustness; Stochastic resonance;
Conference_Titel :
American Control Conference, Proceedings of the 1995
Conference_Location :
Seattle, WA
Print_ISBN :
0-7803-2445-5
DOI :
10.1109/ACC.1995.529316
