容错多智能体优化:III部分
Fault-Tolerant Multi-Agent Optimization: Part III
摘要:
我们研究容错分布式优化的凸(成本)函数的总和与实值标量输入/输出的崩溃故障或拜占庭故障的存在。具体地,目标是优化全局成本函数$\frac{1}{n}\sum_{i\in \mathcal{V}} h_i(x)$,其中$\mathcal{V}=\{1, \ldots, n\}$是代理的集合,并且$h_i(x)$是代理$i$的局部成本函数,其最初仅为代理$i$所知。由于上述全局成本函数不能在崩溃故障或拜占庭故障的存在下精确地优化,我们分别定义了崩溃故障和拜占庭故障的问题的两个较弱版本。当某些代理可能崩溃时,较弱问题的目标是生成作为形成为$$C(\sum_{i\in \mathcal{N}} h_i(x)+\sum_{i\in \mathcal{F}} α_i h_i(x)),$$的函数的最优输出,其中$\mathcal{N}$是非故障代理的集合,$\mathcal{F}$是故障代理(崩溃的代理)的集合,每个$i\in \mathcal{F}$的$0\le α_i\le 1$和$C$是归一化常数,使得$C(|\mathcal{N}|+\sum_{i\in \mathcal{F}} α_i)=1$。我们提出了一个迭代算法,其中每个代理只需要执行本地计算,每次迭代发送一个消息。当一些代理可能是拜占庭式的时,系统不能充分利用由非故障代理保存的数据。相关联的较弱问题的目标是生成作为形成为$$\sum_{i\in \mathcal{N}}α_i h_i(x),$$的函数的最优输出,使得对于每个$i\in \mathcal{N}$和$\sum_{i\in \mathcal{N}}α_i=1$,$α_i\geq 0$。我们提出了一个迭代算法,只需要本地计算,每个代理只有一个消息发送在每次迭代中,确保至少$|\mathcal{N}|-f$代理的权重($α_i$的)是由$\frac{1}{2(|\mathcal{N}|-f)}$下界。
英文摘要:
We study fault-tolerant distributed optimization of a sum of convex (cost) functions with real-valued scalar input/output in the presence of crash faults or Byzantine faults. In particular, the goal is to optimize a global cost function $\frac{1}{n}\sum_{i\in \mathcal{V}} h_i(x)$, where $\mathcal{V}=\{1, \ldots, n\}$ is the collection of agents, and $h_i(x)$ is agent $i$'s local cost function, which is initially known only to agent $i$. Since the above global cost function cannot be optimized exactly in presence of crash faults or Byzantine faults, we define two weaker versions of the problem for crash faults and Byzantine faults, respectively. When some agents may crash, the goal for the weaker problem is to generate an output that is an optimum of a function formed as $$C(\sum_{i\in \mathcal{N}} h_i(x)+\sum_{i\in \mathcal{F}} α_i h_i(x)),$$ where $\mathcal{N}$ is the set of non-faulty agents, $\mathcal{F}$ is the set of faulty agents (crashed agents), $0\le α_i\le 1$ for each $i\in \mathcal{F}$ and $C$ is a normalization constant such that $C(|\mathcal{N}|+\sum_{i\in \mathcal{F}} α_i)=1$. We present an iterative algorithm in which each agent only needs to perform local computation, and send one message per iteration. When some agents may be Byzantine, the system cannot take full advantage of the data kept by non-faulty agents. The goal for the associated weaker problem is to generate an output that is an optimum of a function formed as $$\sum_{i\in \mathcal{N}}α_i h_i(x),$$ such that $α_i\geq 0$ for each $i\in \mathcal{N}$ and $\sum_{i\in \mathcal{N}}α_i=1$. We present an iterative algorithm, where only local computation is needed and only one message per agent is sent in each iteration, that ensures that at least $|\mathcal{N}|-f$ agents have weights ($α_i$'s) that are lower bounded by $\frac{1}{2(|\mathcal{N}|-f)}$.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。