What happens when optimization meets complexity? This project dives into the behavior of Stochastic Gradient Descent (SGD) when facing non-convex functions, those with multiple local minima, plateaus, ...

This is the implementation of the differentiable optimization layer. This project features the ability to differentiate through a non-convex solver like scipy.minimize function. We mainly use ...

In this work, we study special form of non-smooth min-max games when the objective function is (strongly) convex with respect to one of the player's decision variable. We show that a simple multi-step ...

I believe this is what Legendre did and then that what Fenchel did was to generalize this to non-differentiable functions. For non-differentiable functions, we can’t talk about tangent lines and ...

4 convex differentiable functions: the basic algorithm In this section we study the performance of algorithms for the unconstrained minimization of differentiable convex functions. Quadratic functions ...