Meta-Learning Algorithms and their Applications to Quantum Computing
APA
Kallada, M. (2020). Meta-Learning Algorithms and their Applications to Quantum Computing. Perimeter Institute. https://pirsa.org/20010095
MLA
Kallada, Mat. Meta-Learning Algorithms and their Applications to Quantum Computing. Perimeter Institute, Jan. 28, 2020, https://pirsa.org/20010095
BibTex
@misc{ pirsa_PIRSA:20010095, doi = {10.48660/20010095}, url = {https://pirsa.org/20010095}, author = {Kallada, Mat}, keywords = {Condensed Matter}, language = {en}, title = {Meta-Learning Algorithms and their Applications to Quantum Computing}, publisher = {Perimeter Institute}, year = {2020}, month = {jan}, note = {PIRSA:20010095 see, \url{https://pirsa.org}} }
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.