Bibliographic Details
| Title: |
Non-asymptotic Error Bounds For Constant Stepsize Stochastic Approximation For Tracking Mobile Agents |
| Authors: |
Kumar, Bhumesh, Borkar, Vivek, Shetty, Akhil |
| Source: |
Mathematics of Control, Signals, and Systems (2019) |
| Publication Year: |
2018 |
| Subject Terms: |
Electrical Engineering and Systems Science - Signal Processing |
| More Details: |
This work revisits the constant stepsize stochastic approximation algorithm for tracking a slowly moving target and obtains a bound for the tracking error that is valid for the entire time axis, using the Alekseev non-linear variation of constants formula. It is the first non-asymptptic bound for the entire time axis in the sense that it is not based on the vanishing stepsize limit and associated limit theorems unlike prior works, and captures clearly the dependence on problem parameters and the dimension.
Comment: Expanded and revised |
| Document Type: |
Working Paper |
| DOI: |
10.1007/s00498-019-00249-4 |
| Access URL: |
http://arxiv.org/abs/1802.07759 |
| Accession Number: |
edsarx.1802.07759 |
| Database: |
arXiv |
