Distributed Self-Paced Learning in Alternating Direction Method of Multipliers

TL;DR

This paper introduces a distributed self-paced learning method that enables large-scale datasets to be trained efficiently by parallelizing model and instance weight optimization using ADMM, with proven convergence.

Contribution

It reformulates self-paced learning into a distributed framework and proposes a novel algorithm that allows parallel optimization with convergence guarantees.

Findings

Outperforms existing methods on synthetic datasets

Effective on real large-scale datasets

Converges under mild conditions

Abstract

Self-paced learning (SPL) mimics the cognitive process of humans, who generally learn from easy samples to hard ones. One key issue in SPL is the training process required for each instance weight depends on the other samples and thus cannot easily be run in a distributed manner in a large-scale dataset. In this paper, we reformulate the self-paced learning problem into a distributed setting and propose a novel Distributed Self-Paced Learning method (DSPL) to handle large-scale datasets. Specifically, both the model and instance weights can be optimized in parallel for each batch based on a consensus alternating direction method of multipliers. We also prove the convergence of our algorithm under mild conditions. Extensive experiments on both synthetic and real datasets demonstrate that our approach is superior to those of existing methods.