Refine
Year of publication
- 2021 (2)
Document Type
- Article (2)
Language
- English (2)
Has Fulltext
- no (2)
Is part of the Bibliography
- no (2)
Institute
Several learning problems involve solving min-max problems, e.g., empirical distributional robust learning
[Namkoong and Duchi, 2016, Curi et al., 2020] or learning with non-standard aggregated losses [Shalev-
Shwartz and Wexler, 2016, Fan et al., 2017]. More specifically, these problems are convex-linear problems
where the minimization is carried out over the model parameters w ∈ W and the maximization over the
empirical distribution p ∈ K of the training set indexes, where K is the simplex or a subset of it. To design
efficient methods, we let an online learning algorithm play against a (combinatorial) bandit algorithm.
We argue that the efficiency of such approaches critically depends on the structure of K and propose two
properties of K that facilitate designing efficient algorithms. We focus on a specific family of sets Sn,k
encompassing various learning applications and provide high-probability convergence guarantees to the
minimax values.
Linear bandit algorithms yield O~(n√T) pseudo-regret bounds on compact convex action sets K⊂Rn and two types of structural assumptions lead to better pseudo-regret bounds. When K is the simplex or an ℓp ball with p∈]1,2], there exist bandits algorithms with O~(√n√T) pseudo-regret bounds. Here, we derive bandit algorithms for some strongly convex sets beyond ℓp balls that enjoy pseudo-regret bounds of O~(√n√T), which answers an open question from [BCB12, §5.5.]. Interestingly, when the action set is uniformly convex but not necessarily strongly convex, we obtain pseudo-regret bounds with a dimension dependency smaller than O(√n). However, this comes at the expense of asymptotic rates in T varying between O(√T) and O(T).