separation oracle
A Near-optimal Algorithm for Learning Margin Halfspaces with Massart Noise
In this paper, we study the same problem in the Massart noise model that we now define.
Riemannian Projection-free Online Learning
In Euclidean space, OCO boasts a robust theoretical foundation and numerous real-world applications, such as online load balancing (Molinaro, 2017), optimal control (Li et al., 2019), revenue maximization (Lin et al., 2019), and portfolio management (Jรฉzรฉquel et al., 2022).
Learning Safe Policies with Expert Guidance
Jessie Huang, Fa Wu, Doina Precup, Yang Cai
Neural Information Processing Systems http://nips.cc/
ContextualRecommendationsandLow-Regret Cutting-PlaneAlgorithms AnonymousAuthor(s) Affiliation Address email
We wish to2 learn a hiddend-dimensional valuew . Every round, we are presented with a3 subset Xt Rd of possible actions.
ContextualRecommendationsandLow-Regret Cutting-PlaneAlgorithms
We wish to learn a hiddend-dimensional valuew . Every round, we are presented with a subset Xt Rd of possible actions.
Memory-Constrained Algorithms for Convex Optimization
As a summary, this paper makes the following contributions.