Work

Non-Asymptotic Convergence Analysis of the Multiplicative Gradient Algorithm for the Log-Optimal Investment Problems

Year: 2021

Type: preprint

Abstract: We analyze the non-asymptotic convergence rate of the multiplicative gradient (MG) algorithm for the log-optimal investment problems, and show that it exhibits $O(1/t)$ convergence rates, in both ergodic and non-ergodic senses.

Source: arXiv (Cornell University)

Author: Renbo Zhao

Institution: Massachusetts Institute of Technology

Language: English

Topic: Risk and Portfolio Optimization

Subfield: Management Science and Operations Research

Field: Decision Sciences

Domain: Social Sciences

Open Access status: green

OpenAlex ID: W3200538081

Cites: 13

Cited by:

Related to: 10