Showing 2023Show all
3 papers · 1 filter
cs.LG2023
Ahpatron: A New Budgeted Online Kernel Learning Machine with Tighter Mistake Bound
Yun Liao, Junfan Li, Shizhong Liao +2
In this paper, we study the mistake bound of online kernel learning on a budget. We propose a new budgeted online kernel learning model, called Ahpatron, which significantly improv…
cs.LG2023
Nearly Optimal Algorithms with Sublinear Computational Complexity for Online Kernel Regression
Junfan Li, Shizhong Liao
The trade-off between regret and computational cost is a fundamental problem for online kernel regression, and previous algorithms worked on the trade-off can not keep optimal regr…
cs.LG2023
Improved Regret Bounds for Online Kernel Selection under Bandit Feedback
Junfan Li, Shizhong Liao
In this paper, we improve the regret bound for online kernel selection under bandit feedback. Previous algorithm enjoys a $O((\Vert f\Vert^2_{\mathcal{H}_i}+1)K^{\frac{1}{3}}T^{\fr…