Tommaso Giovannelli

Bilevel stochastic methods for optimization and machine learning: Bilevel stochastic descent and DARTS.

2021 · arXiv (Cornell University)

Two-level stochastic optimization formulations have become instrumental in a number of machine learning contexts such as neural architecture search, continual learning, adversarial learning, and hyperparameter tuning. Practical stochastic bilevel optimization problems become challenging in optimization …