Scale-Free Algorithms for Online Linear Optimization
نویسندگان
چکیده
We design algorithms for online linear optimization that have optimal regret and at the same time do not need to know any upper or lower bounds on the norm of the loss vectors. We achieve adaptiveness to norms of loss vectors by scale invariance, i.e., our algorithms make exactly the same decisions if the sequence of loss vectors is multiplied by any positive constant. Our algorithms work for any decision set, bounded or unbounded. For unbounded decisions sets, these are the first truly adaptive algorithms for online linear optimization.
منابع مشابه
Open Problem: Parameter-Free and Scale-Free Online Algorithms
Existing vanilla algorithms for online linear optimization have O((ηR(u) + 1/η) √ T ) regret with respect to any competitor u, whereR(u) is a 1-strongly convex regularizer and η > 0 is a tuning parameter of the algorithm. For certain decision sets and regularizers, the so-called parameter-free algorithms have Õ( √ R(u)T ) regret with respect to any competitor u. Vanilla algorithm can achieve th...
متن کاملScale-free online learning
We design and analyze algorithms for online linear optimization that have optimal regret and at the same time do not need to know any upper or lower bounds on the norm of the loss vectors. Our algorithms are instances of the Follow the Regularized Leader (FTRL) and Mirror Descent (MD) meta-algorithms. We achieve adaptiveness to the norms of the loss vectors by scale invariance, i.e., our algori...
متن کاملThe Price of Differential Privacy for Online Learning
We design differentially private algorithms for the problem of online linear optimization in the full information and bandit settings with optimal Õ( √ T ) regret bounds. In the full-information setting, our results demonstrate that ε-differential privacy may be ensured for free – in particular, the regret bounds scale as O( √ T ) + Õ ( 1 ε ) . For bandit linear optimization, and as a special c...
متن کاملProjection-free Online Learning
The computational bottleneck in applying online learning to massive data sets is usually the projection step. We present efficient online learning algorithms that eschew projections in favor of much more efficient linear optimization steps using the Frank-Wolfe technique. We obtain a range of regret bounds for online convex optimization, with better bounds for specific cases such as stochastic ...
متن کاملThe Price of Differential Privacy for Online Learning(with Supplementary Material)
We design differentially private algorithms for the problem of online linear optimization in the full information and bandit settings with optimal Õ( √ T )1 regret bounds. In the full-information setting, our results demonstrate that ε-differential privacy may be ensured for free – in particular, the regret bounds scale as O( √ T ) + Õ ( 1 ε ) . For bandit linear optimization, and as a special ...
متن کامل