86 citations · 685 across the 45 of their papers we have counts for
4 papers · 1 filter
Faster One-Sample Stochastic Conditional Gradient Method for Composite Convex Minimization
Gideon Dresdner, Maria-Luiza Vladarean, Gunnar Rätsch +3
We propose a stochastic conditional gradient method (CGM) for minimizing convex finite-sum objectives formed as a sum of smooth and non-smooth terms. Existing CGM variants for this…
Improved Optimistic Algorithms for Logistic Bandits
Louis Faury, Marc Abeille, Clément Calauzènes +1
The generalized linear bandit framework has attracted a lot of attention in recent years by extending the well-understood linear setting and allowing to model richer reward structu…
SDNA: Stochastic Dual Newton Ascent for Empirical Risk Minimization
Zheng Qu, Peter Richtárik, Martin Takáč +1
We propose a new algorithm for minimizing regularized empirical loss: Stochastic Dual Newton Ascent (SDNA). Our method is dual in nature: in each iteration we update a random subse…
Parallel coordinate descent for the Adaboost problem
Olivier Fercoq
We design a randomised parallel version of Adaboost based on previous studies on parallel coordinate descent. The algorithm uses the fact that the logarithm of the exponential loss…