Presents a new algorithm for optimal transport problems, showing speed and performance improvements, with applications in domain adaptation and generative models.
Explores primal-dual optimization methods, focusing on Lagrangian approaches and various methods like penalty, augmented Lagrangian, and splitting techniques.
Discusses optimization techniques in machine learning, focusing on stochastic gradient descent and its applications in constrained and non-convex problems.
Explores Sum of Squares polynomials and Semidefinite Programming in Polynomial Optimization, enabling the approximation of non-convex polynomials with convex SDP.