In many applications, learning systems are required to process continuous
non-stationary data streams. We study this problem in an online learning
framework and propose an algorithm that can deal with adversarial time-varying
and nonlinear constraints. As we show in our work, the algorithm called
Constraint Violation Velocity Projection (CVV-Pro) achieves $\sqrt{T}$ regret
and converges to the feasible set at a rate of $1/\sqrt{T}$, despite the fact
that the feasible set is slowly time-varying and a priori unknown to the
learner. CVV-Pro only relies on local sparse linear approximations of the
feasible set and therefore avoids optimizing over the entire set at each
iteration, which is in sharp contrast to projected gradients or Frank-Wolfe
methods. We also empirically evaluate our algorithm on two-player games, where
the players are subjected to a shared constraint.

本研究提出了一种名为 CVV-Pro 的算法，通过利用局部稀疏线性逼近来处理不断变化的非线性约束条件的连续数据流，在面对共享限制的两人博弈时表现良好。

对抗性非线性约束下的在线学习

Online Learning under Adversarial Nonlinear Constraints

Learning from continuous data streams via classification/regression is
prevalent in many domains. Adapting to evolving data characteristics (concept
drift) while protecting data owners' private information is an open challenge.
We present a differentially private ensemble solution to this problem with two
distinguishing features: it allows an \textit{unbounded} number of ensemble
updates to deal with the potentially never-ending data streams under a fixed
privacy budget, and it is \textit{model agnostic}, in that it treats any
pre-trained differentially private classification/regression model as a
black-box. Our method outperforms competitors on real-world and simulated
datasets for varying settings of privacy, concept drift, and data distribution.

该论文提出了一种基于隐私保护的集成学习方法，旨在应对连续数据流且涉及数据漂移的场景，该方法可以应对不断增长的数据流以及模型的升级更新，并适用于不同类型的预训练隐私分类 / 回归模型。在实际和模拟数据集上进行的实验表明，在不同的隐私、概念漂移和数据分布设置下，该方法表现优异。

数据流的差分隐私集成分类器

Differentially Private Ensemble Classifiers for Data Streams

The advance of Internet and Sensor technology has brought about new
challenges evoked by the emergence of continuous data streams. Beyond rapid
data processing, application areas like ambient assisted living, robotics, or
dynamic scheduling involve complex reasoning tasks. We address such scenarios
and elaborate upon approaches to knowledge-intense stream reasoning, based on
Answer Set Programming (ASP). While traditional ASP methods are devised for
singular problem solving, we develop new techniques to formulate and process
problems dealing with emerging as well as expiring data in a seamless way.

通过使用 ASP 技术，本研究在解决物联网、传感器技术、连续数据流、流推理等领域中的关键问题。