1. Structured sparsity-inducing norms through submodular functions;Bach, Francis;Advances in Neural Information Processing Systems,2010
2. Duality between subgradient and conditional gradient methods;Bach, Francis;SIAM J. Optim.,2015
3. A descent lemma beyond Lipschitz gradient continuity: first-order methods revisited and applications;Bauschke, Heinz H.;Math. Oper. Res.,2017
4. [4] Bauschke, Heinz H.; Combettes, Patrick L. Convex Analysis and Monotone Operator Theory in Hilbert Spaces, 408, Springer, 2011
5. [5] Berrada, Leonard; Zisserman, Andrew; Kumar, M. Pawan Deep Frank-Wolfe for neural network optimization (2018) (https://arxiv.org/abs/1811.07591)