← Search

Benjamin Dubois-Taine

2 accepted papers

2022

Fast Stochastic Composite Minimization and an Accelerated Frank-Wolfe Algorithm under Parallelization

NeurIPS 2022accept

We consider the problem of minimizing the sum of two convex functions. One of those functions has Lipschitz-continuous gradients, and can be accessed via stochastic oracles, whereas the other is ``simple''. We provide a Bregman-type algorithm with accelerated convergence in function values to a ball…

2022

Towards Noise-adaptive, Problem-adaptive (Accelerated) Stochastic Gradient Descent

ICML 2022oral

We aim to make stochastic gradient descent (SGD) adaptive to (i) the noise $\sigma^2$ in the stochastic gradients and (ii) problem-dependent constants. When minimizing smooth, strongly-convex functions with condition number $\kappa$, we prove that $T$ iterations of SGD with exponentially decreasing…