In recent years, the ML community has seen surges of interest in both adversarially robust learning and implicit layers, but connections between these two areas have seldom been explored.
Large optimization problems with hard constraints arise in many settings, yet classical solvers are often prohibitively slow, motivating the use of deep networks as cheap "approximate solvers."
When designing controllers for safety-critical systems, practitioners often face a challenging tradeoff between robustness and performance.
2 code implementations • 10 Jun 2019 • David Rolnick, Priya L. Donti, Lynn H. Kaack, Kelly Kochanski, Alexandre Lacoste, Kris Sankaran, Andrew Slavin Ross, Nikola Milojevic-Dupont, Natasha Jaques, Anna Waldman-Brown, Alexandra Luccioni, Tegan Maharaj, Evan D. Sherwin, S. Karthik Mukkavilli, Konrad P. Kording, Carla Gomes, Andrew Y. Ng, Demis Hassabis, John C. Platt, Felix Creutzig, Jennifer Chayes, Yoshua Bengio
Climate change is one of the greatest challenges facing humanity, and we, as machine learning experts, may wonder how we can help.
We demonstrate that by integrating this solver into end-to-end learning systems, we can learn the logical structure of challenging problems in a minimally supervised fashion.
Ranked #1 on Game of Suduko on Sudoko 9x9
With the increasing popularity of machine learning techniques, it has become common to see prediction algorithms operating within some larger process.