NOTE: We are starting to host hybrid (zoom + in-person) MRMs as we return to the campus. You can now attend MRMs in person at Bankstown Campus.
Join us at the next MRM with invited speaker PhD Candidate Siri Padmanabhan Poti to present 'Iterative Robust Search (iRoSe): A framework for coevolutionary hyperparameter optimisation.'
Topic: Iterative Robust Search (iRoSe): A framework for coevolutionary hyperparameter optimisation Speaker: Siri Padmanabhan Poti
Extant hyperparameter optimisation approaches that search out optima within large combinatorial search spaces randomly or non-specifically when viewed through the 'No-Free-Lunches' theorem is a priori unjustifiable. An iterative Robust Search (iRoSe) hyperparameter optimisation framework is formulated that robustifies optimisation in a coevolutionary, adaptive manner by leveraging gain in Signal-to-Noise Ratio (SNR). iRoSe abstracts out the complexity of the learning algorithm through 'macro modelling in terms of signal, control, noise and response. Designed sets of 'proportionally balanced' trials are run, followed by a 'main effects analysis' of SNR from hyperparameter values. iRoSe iteratively converges onto configurations that produce an effective gain in performance characteristics.
MARCS staff and students are reminded that all meetings and workshops have an important role in building and maintaining the sense of community which is central to the success of MARCS as a cooperative and energetic research institute.
Disclaimer: MRM meetings may be recorded on Zoom for future access to MARCS members and subject to speaker's approval
