TY - GEN
T1 - A Closed Loop Gradient Descent Algorithm applied to Rosenbrock's function
AU - Bhattacharjee, Subhransu S.
AU - Petersen, Ian R.
N1 - Publisher Copyright:
© 2021 IEEE.
PY - 2021
Y1 - 2021
N2 - We introduce a novel adaptive damping technique for an inertial gradient system which finds application as a gradient descent algorithm for unconstrained optimisation. In an example using the non-convex Rosenbrock's function, we show an improvement on existing momentum-based gradient optimisation methods. Also using Lyapunov stability analysis, we demonstrate the performance of the continuous-time version of the algorithm. Using numerical simulations, we consider the performance of its discrete-time counterpart obtained by using the symplectic Euler method of discretisation.
AB - We introduce a novel adaptive damping technique for an inertial gradient system which finds application as a gradient descent algorithm for unconstrained optimisation. In an example using the non-convex Rosenbrock's function, we show an improvement on existing momentum-based gradient optimisation methods. Also using Lyapunov stability analysis, we demonstrate the performance of the continuous-time version of the algorithm. Using numerical simulations, we consider the performance of its discrete-time counterpart obtained by using the symplectic Euler method of discretisation.
KW - Learning Systems
KW - Nonlinear Systems and Control
KW - Time-varying Systems
UR - http://www.scopus.com/inward/record.url?scp=85123598366&partnerID=8YFLogxK
U2 - 10.1109/ANZCC53563.2021.9628258
DO - 10.1109/ANZCC53563.2021.9628258
M3 - Conference contribution
T3 - 2021 Australian and New Zealand Control Conference, ANZCC 2021
SP - 137
EP - 142
BT - 2021 Australian and New Zealand Control Conference, ANZCC 2021
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 2021 Australian and New Zealand Control Conference, ANZCC 2021
Y2 - 25 November 2021 through 26 November 2021
ER -