改进的结构和几何集合系统的在线击中集算法

带长期约束的凸函数追踪

Chasing Convex Functions with Long-term Constraints

该研究提出带长期约束的在线凸函数追踪问题，针对有界击中成本梯度与加权度量场景，设计最优竞争及学习增强算法，可应用于可持续能源与计算系统的在线资源分配。

Smoothed Online Optimization with Unreliable Predictions

We examine the problem of smoothed online optimization, where a decision maker must sequentially choose points in a normed vector space to minimize the sum of per-round, non-convex hitting costs and the costs of switching decisions between rounds. The decision maker has access to a black-box oracle, such as a machine learning model, that provides untrusted and potentially inaccurate predictions of the optimal decision in each round. The goal of the decision maker is to exploit the predictions if they are accurate, while guaranteeing performance that is not much worse than the hindsight optimal…

最优去中心化平滑在线凸优化

Optimal Decentralized Smoothed Online Convex Optimization

针对多智能体平滑在线凸优化问题，提出了首个可证明渐近最优的去中心化算法ACORD，仅依赖局部信息即可实现低计算复杂度，且性能优于现有LPC算法。

Structured Robust Submodular Maximization: Offline and Online Algorithms

Constrained submodular function maximization has been used in subset selection problems such as selection of most informative sensor locations. While these models have been quite popular, the solutions Constrained submodular function maximization has been used in subset selection problems such as selection of most informative sensor locations. While these models have been quite popular, the solutions obtained via this approach are unstable to perturbations in data defining the submodular functions. Robust submodular maximization has been proposed as a richer model that aims to overcome this di…

用于在线数据流快速且内存高效管理的结构化下采样

Structured Downsampling for Fast, Memory-efficient Curation of Online Data Streams

提出DStream算法套件，通过单一更新操作和位级计算实现内存高效、固定容量的数据流滚动下采样，支持平稳、拉伸和倾斜三种时间覆盖标准，并在O(1)时间内完成数据摄入。

Minimalistic Predictions to Schedule Jobs with Online Precedence Constraints

We consider non-clairvoyant scheduling with online precedence constraints, where an algorithm is oblivious to any job dependencies and learns about a job only if all of its predecessors have been completed. Given strong impossibility results in classical competitive analysis, we investigate the problem in a learning-augmented setting, where an algorithm has access to predictions without any quality guarantee. We discuss different prediction models: novel problem-specific models as well as general ones, which have been proposed in previous works. We present lower bounds and algorithmic upper bo…

非平稳在线非凸优化的多点Bandit算法

Multi-Point Bandit Algorithms for Nonstationary Online Nonconvex Optimization

Bandit算法主要是在凸环境下分析的，其性能指标是基于函数值的固定后悔。在本文中，在线强化学习问题的动机，我们提出并分析了一般和结构化的非凸问题与非平稳（或动态）遗憾的性能指标，在随机和非随机设置的强盗算法。首先，对于一般的非凸函数，我们考虑非平稳版本的一阶和二阶固定的解决方案作为一个遗憾的措施，出于类似的性能措施离线非凸优化。在二阶固定解决方案的遗憾的情况下，我们提出并分析在线和土匪版本的立方正则化牛顿的方法。强盗版本是基于估计的海森矩阵的强盗设置，基于二阶高斯斯坦的身份。我们的非平稳遗憾界的二阶固定的解决方案有有趣的后果，避免鞍点的强盗设置。其次，对于弱拟凸函数和单调弱次模函数，我们考虑用函数值表示的非平稳后悔测度;这样的非凸函数的结构类使得人们可以考虑用函数值定义的后悔测度，类似于凸函数。对于这种情况下的功能值，和一阶固定的解决方案为基础的遗憾措施，我们提供遗憾的界限，在低维和高维的设置，在某些情况下。