3 papers
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…
cs.LG2022
Improved Kernel Alignment Regret Bound for Online Kernel Learning
Junfan Li, Shizhong Liao
In this paper, we improve the kernel alignment regret bound for online kernel learning in the regime of the Hinge loss function. Previous algorithm achieves a regret of $O((\mathca…