-
Multi-armed Bandit Problem with Known Trend
Multi-armed bandit problem with known trend -
Optimality of Robust Online Learning
The dataset used in this paper is a sequence of random samples independently distributed from a probability distribution ρ. -
Pricing Mechanism for Resource Sustainability in Competitive Online Learning ...
The dataset used in the paper is a multi-agent system with competing online learning agents. The dataset is used to evaluate the proposed pricing mechanism for resource... -
Efficient Algorithms for Online Decision Problems
An efficient algorithm for online decision problems. -
Mondrian Forests
The dataset used in this paper is a collection of i.i.d. sequences (X1, Y1), (X2, Y2)... of [0, 1]d × {0, 1}-valued random variables that come sequentially, such that each (Xi,... -
Minimax Regret for Online Learning with Feedback Graphs
The dataset used in the paper is a sequence of strongly observable undirected feedback graphs, where each graph has independence number α for some common value α. -
Online Nonlinear Estimation via Iterative L2-Space Projections
The proposed online learning paradigm is a significant extension of the conventional kernel adaptive filtering framework from RKHS to the space L2(RL, dµ) which has no... -
Online Pricing with Offline Data
The dataset used in the paper is a collection of historical prices and demand observations for a single product with infinite amount of inventory over a selling horizon of T...