PIRSA ID: 20010095
Série : Quantum Matter Machine Learning Initiative
Event Type: Seminar
Domaine(s) scientifique(s) : Quantum Matter
Date de fin : 2020-01-28
Speaker(s): Mat Kallada Mila
Meta-learning involves learning mathematical devices using problem instances as training data. In this talk, we first describe recent meta-learning approaches involving the learning of objects such as: initial weights, parameterized losses, hyper-parameter search strategies, and samplers. We then discuss learned optimizers in further detail and their applications towards optimizing variational circuits. This talk also covers some lessons learned starting a spin-off from academia.