Can We Do Better Than Random Start? The Power of Data Outsourcing

TL;DR

This paper explores how data outsourcing can improve model initialization in machine learning, proposing algorithms that outperform random starts under data sharing constraints, with theoretical guarantees and empirical validation.

Contribution

It introduces simulation-based algorithms leveraging outsourced data to find better initial points for optimization, surpassing random start methods.

Findings

Algorithms outperform random start in experiments

Theoretical guarantees for high-probability success

Effective under data sharing constraints

Abstract

Many organizations have access to abundant data but lack the computational power to process the data. While they can outsource the computational task to other facilities, there are various constraints on the amount of data that can be shared. It is natural to ask what can data outsourcing accomplish under such constraints. We address this question from a machine learning perspective. When training a model with optimization algorithms, the quality of the results often relies heavily on the points where the algorithms are initialized. Random start is one of the most popular methods to tackle this issue, but it can be computationally expensive and not feasible for organizations lacking computing resources. Based on three different scenarios, we propose simulation-based algorithms that can utilize a small amount of outsourced data to find good initial points accordingly. Under suitable regularity conditions, we provide theoretical guarantees showing the algorithms can find good initial points with high probability. We also conduct numerical experiments to demonstrate that our algorithms perform significantly better than the random start approach.