Problem
Research questions and friction points this paper is trying to address.
Worst-case online classification
Sequential complexity
Preview model
Adversarial Online Classification with a Preview
🤖 AI Summary
研究通过预览模型解决最坏情况下的在线分类问题，使用随机预览替代序列复杂度，并提出ChainedPrediction算法实现最优二元边界。
📝 Abstract
Worst-case online classification is governed by sequential complexity, such as Littlestone dimension, and can be impossible even for statistically simple classes, such as thresholds of VC dimension one. We study a preview model in which an oblivious adversary fixes an entire labeled sequence of length $T$, a uniformly random subset of size $pT$ is revealed before prediction begins, and the remaining $(1-p)T$ examples are then presented in their original adversarial order.
Against the best full-sequence hypothesis evaluated on the unrevealed examples, we characterize the dependence on the preview rate $p$: for binary classes of VC dimension $d$, the optimal excess loss is $Θ(d/p+\sqrt{dT})$, up to the trivial cap at $T$; for multiclass classes we obtain the corresponding $\widetilde O(d_{\rm DS}/p+\sqrt{d_{\rm Nat}T})$ bound with no dependence on the number of labels. Thus a random preview can replace worst-case sequential complexity by classical statistical dimensions without randomizing the online order. To achieve the sharp binary bound, our ChainedPrediction algorithm uses an online analogue of chaining, implemented as a multiscale aggregation algorithm rather than only as an analytic argument.
Innovation
Methods, ideas, or system contributions that make the work stand out.
preview model
adversarial online classification
chaining
multiscale aggregation
🔎 Similar Papers
No similar papers found.
