This paper presents OptNet, a network architecture that integrates optimization problems (here, specifically in the form of quadratic programs) as individual layers in larger end-to-end trainable deep networks.
We present Spectral Inference Networks, a framework for learning eigenfunctions of linear operators by stochastic optimization.
Bilevel optimization has been recently revisited for designing and analyzing algorithms in hyperparameter tuning and meta learning tasks.
Empirically, our approach outperforms competing hyperparameter optimization methods on large-scale deep learning problems.
We present SOSELETO (SOurce SELEction for Target Optimization), a new method for exploiting a source dataset to solve a classification problem on a target dataset.
The design of spacecraft trajectories for missions visiting multiple celestial bodies is here framed as a multi-objective bilevel optimization problem.
To remedy this, this paper proposes \mldas, a mixed-level reformulation for NAS that can be optimized efficiently and reliably.
Bilevel optimization problems are at the center of several important machine learning problems such as hyperparameter tuning, data denoising, meta- and few-shot learning, data poisoning.