When: Jun 8th, 2022 – 11:00 – 11:45 AM
Where: Google meet link
1-Lipschitz Neural Networks: a splines-based approach
Lipschitz-constrained neural networks have many applications in machine learning. Since designing and training expressive Lipschitz-constrained networks is very challenging, there is a need for improved methods and a better theoretical understanding. Unfortunately, it turns out that ReLU networks have provable disadvantages in this setting. Hence, other activation functions are proposed, such as GroupSort or Linear Splines. Advantages and issues of their implementation will be addressed and open problems will be discussed.