Scale-Invariant Unconstrained Online Learning
Scale-Invariant Unconstrained Online Learning
复制标题
尺度不变的无约束在线学习
DOI:
10.1016/j.tcs.2019.11.016
复制
发表时间:
2017
期刊:
影响因子:
--
通讯作者:
W. Kotłowski
中科院分区:
文献类型:
--
作者:
W. Kotłowski
We consider an online supervised learning problem, in which both the instances (input vectors) and the comparator (weight vector) are unconstrained. We exploit a natural scale invariance symmetry in our unconstrained setting: the predictions of the optimal comparator are invariant under any linear transformation of the instances. Our goal is to design online algorithms which also enjoy this property, i.e. are scale-invariant. We start with the case of coordinate-wise invariance, in which the individual coordinates (features) can be arbitrarily rescaled. We give an algorithm, which achieves essentially optimal regret bound in this setup, expressed by means of a coordinate-wise scale-invariant norm of the comparator. We then study general invariance with respect to arbitrary linear transformations. We first give a negative result, showing that no algorithm can achieve a meaningful bound in terms of scale-invariant norm of the comparator in the worst case. Next, we compliment this result with a positive one, providing an algorithm which “almost” achieves the desired bound, incurring only a logarithmic overhead in terms of the relative size of the instances.
DOI:
--
发表时间:
2017
期刊:
Advances in Neural Information Processing Systems 30
影响因子:
--
作者:
Orabona, Francesco;Tommasi, Tatiana
通讯作者:
Tommasi, Tatiana