Tight bounds for collaborative PAC learning via multiplicative weights

Jiecao Chen, Qin Zhang, Yuan Zhou

Research output: Contribution to journalConference articlepeer-review

Abstract

We study the collaborative PAC learning problem recently proposed in Blum et al. [3], in which we have k players and they want to learn a target function collaboratively, such that the learned function approximates the target function well on all players' distributions simultaneously. The quality of the collaborative learning algorithm is measured by the ratio between the sample complexity of the algorithm and that of the learning algorithm for a single distribution (called the overhead). We obtain a collaborative learning algorithm with overhead O(ln k), improving the one with overhead O(ln2 k) in [3]. We also show that an Ω(ln k) overhead is inevitable when k is polynomial bounded by the VC dimension of the hypothesis class. Finally, our experimental study has demonstrated the superiority of our algorithm compared with the one in Blum et al. [3] on real-world datasets.

Original languageEnglish (US)
Pages (from-to)3598-3607
Number of pages10
JournalAdvances in Neural Information Processing Systems
Volume2018-December
StatePublished - 2018
Event32nd Conference on Neural Information Processing Systems, NeurIPS 2018 - Montreal, Canada
Duration: Dec 2 2018Dec 8 2018

ASJC Scopus subject areas

  • Computer Networks and Communications
  • Information Systems
  • Signal Processing

Fingerprint

Dive into the research topics of 'Tight bounds for collaborative PAC learning via multiplicative weights'. Together they form a unique fingerprint.

Cite this