@inproceedings{DiakonikolasCardereraPokutta, author = {Diakonikolas, Jelena and Carderera, Alejandro and Pokutta, Sebastian}, title = {Breaking the Curse of Dimensionality (Locally) to Accelerate Conditional Gradients}, series = {OPTML Workshop Paper}, booktitle = {OPTML Workshop Paper}, language = {en} } @inproceedings{DiakonikolasCardereraPokutta, author = {Diakonikolas, Jelena and Carderera, Alejandro and Pokutta, Sebastian}, title = {Locally Accelerated Conditional Gradients}, series = {Proceedings of AISTATS}, booktitle = {Proceedings of AISTATS}, language = {en} } @inproceedings{CardereraDiakonikolasLinetal., author = {Carderera, Alejandro and Diakonikolas, Jelena and Lin, Cheuk Yin and Pokutta, Sebastian}, title = {Parameter-free Locally Accelerated Conditional Gradients}, series = {ICML 2021}, booktitle = {ICML 2021}, abstract = {Projection-free conditional gradient (CG) methods are the algorithms of choice for constrained optimization setups in which projections are often computationally prohibitive but linear optimization over the constraint set remains computationally feasible. Unlike in projection-based methods, globally accelerated convergence rates are in general unattainable for CG. However, a very recent work on Locally accelerated CG (LaCG) has demonstrated that local acceleration for CG is possible for many settings of interest. The main downside of LaCG is that it requires knowledge of the smoothness and strong convexity parameters of the objective function. We remove this limitation by introducing a novel, Parameter-Free Locally accelerated CG (PF-LaCG) algorithm, for which we provide rigorous convergence guarantees. Our theoretical results are complemented by numerical experiments, which demonstrate local acceleration and showcase the practical improvements of PF-LaCG over non-accelerated algorithms, both in terms of iteration count and wall-clock time.}, language = {en} }