Anis Hamadouche is a final-year PhD student from
Heriot-Watt University. Mr. Hamadouche’s
work consists of theoretically analyzing the performance of iterative
optimization algorithms, such as proximal algorithms and
alternating direction method of multipliers (ADMM), when the
internal operations of the algorithms are executed with errors.
The types of errors considered stem from approximations at hardware
and software levels, for example, quantization under different types of
numerical representations, including fixed- and floating-point
representations. Although this work is very theoretical, it has
wide-ranging implications. In fact, in contrast with prior work, it
considers realistic error models and implementation in platforms like FPGAs.
Mr. Hamadouche’s PhD is associated
with the UDRC Phase III programme (https://udrc.eng.ed.ac.uk/),
sponsored by UKRI’s EPSRC and the MoD. And, in this context, it has
explored applications in defense, for example, planning and control of
drone trajectories, and image processing.