There's a fascinating link between minimization of quadratic functions and polynomials. A link
deep and allows to phrase optimization problems in the language of polynomials and vice versa.
Using this connection, we can tap into centuries of research in the theory of polynomials and
shed new light on …
This blog post extends the convergence theory from the first part of these notes on the
Frank-Wolfe (FW) algorithm with convergence guarantees on the primal-dual gap which generalize
and strengthen the convergence guarantees obtained in the first part.
The main contribution is to develop a parallel (fully asynchronous, no locks) variant of the SAGA algorighm. This is a stochastic variance-reduced method for general optimization, specially adapted for problems …