击败乘性权值更新算法
Beating the Multiplicative Weights Update Algorithm
摘要:
乘性权值更新算法已被广泛用于设计许多计算任务的迭代算法。其核心思想是维护一组专家的分布,并根据底层优化问题的参数在线更新此分布。在这份报告中,我们研究了一种特殊的MWU算法的行为,该算法用于在存在篡改专家建议的对手的情况下生成全局抛硬币。具体来说,我们将注意力集中在两种对抗策略上:(1)非自适应,其中对手先验地选择一组固定的专家,并在每一轮中破坏他们的建议;(2)自适应,其中随着算法的进展而选择该组。我们将这些对抗策略制定为贪婪策略,试图最大化MWU计算的最终加权建议中腐败专家的份额,并提供需要解决的底层优化问题以实现这一目标。我们提供的实证结果表明,在上述任何一个对手的存在下,MWU算法需要$\mathcal{O}(n)$轮预期产生所需的输出。该结果与$\mathcal{O}(n^3)$用于一般拜占庭共识问题的当前技术状态相比很好。最后,我们简要讨论了这些对抗策略的扩展一般MWU算法,并提供了一个框架的轮廓在该设置。
英文摘要:
Multiplicative weights update algorithms have been used extensively in designing iterative algorithms for many computational tasks. The core idea is to maintain a distribution over a set of experts and update this distribution in an online fashion based on the parameters of the underlying optimization problem. In this report, we study the behavior of a special MWU algorithm used for generating a global coin flip in the presence of an adversary that tampers the experts' advice. Specifically, we focus our attention on two adversarial strategies: (1) non-adaptive, in which the adversary chooses a fixed set of experts a priori and corrupts their advice in each round; and (2) adaptive, in which this set is chosen as the rounds of the algorithm progress. We formulate these adversarial strategies as being greedy in terms of trying to maximize the share of the corrupted experts in the final weighted advice the MWU computes and provide the underlying optimization problem that needs to be solved to achieve this goal. We provide empirical results to show that in the presence of either of the above adversaries, the MWU algorithm takes $\mathcal{O}(n)$ rounds in expectation to produce the desired output. This result compares well with the current state of the art of $\mathcal{O}(n^3)$ for the general Byzantine consensus problem. Finally, we briefly discuss the extension of these adversarial strategies for a general MWU algorithm and provide an outline for the framework in that setting.
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。