We consider the problem of online classification under a privacy constraint. In this setting a learner observes sequentially a stream of labelled examples $(x_t, y_t)$, for $1 \leq t \leq T$, and returns at each iteration $t$ a hypothesis $h_t$ which is used to predict the label of each new example $x_t$. The learner's performance is measured by her regret against a known hypothesis class $\mathcal{H}$. We require that the algorithm satisfies the following privacy constraint: the sequence $h_1, \ldots, h_T$ of hypotheses output by the algorithm needs to be an $(\epsilon, \delta)$-differentially private function of the whole input sequence $(x_1, y_1), \ldots, (x_T, y_T)$. We provide the first non-trivial regret bound for the realizable setting. Specifically, we show that if the class $\mathcal{H}$ has constant Littlestone dimension then, given an oblivious sequence of labelled examples, there is a private learner that makes in expectation at most $O(\log T)$ mistakes -- comparable to the optimal mistake bound in the non-private case, up to a logarithmic factor. Moreover, for general values of the Littlestone dimension $d$, the same mistake bound holds but with a doubly-exponential in $d$ factor. A recent line of work has demonstrated a strong connection between classes that are online learnable and those that are differentially-private learnable. Our results strengthen this connection and show that an online learning algorithm can in fact be directly privatized (in the realizable setting). We also discuss an adaptive setting and provide a sublinear regret bound of $O(\sqrt{T})$.
翻译:我们考虑在隐私限制下在线分类的问题 。 在此设置中, 学习者会按顺序观察一系列贴有标签的示例 $( x_ t, y_ t) 美元, $\ leq t\ leq T$ 美元, 并在每次迭代时返回 $t美元 假设 $t美元 美元, 用于预测每个新例的标签 $x_ t美元。 学习者的表现是通过她对已知假设等级$\ mathcal{ H} 美元进行测量的。 我们要求算法满足以下隐私限制 : $_ 1, eldots, h_ t$ 美元 的顺序是 $ (\ lex_ 1, y_ 1,\ t) 美元 美元 。 学习者对每个新例的 $x_ d, (x_ T, y_ T) 的成绩是第一个非三连锁的 。 具体地说, 我们显示如果 $\\ cal_ cal_ 美元 之间的连线连接是恒的, 那么, litteststststest listate listate liver liver