Bootstrap Model Aggregation for Distributed Statistical Learning
This addresses the challenge of model aggregation in distributed settings, which is incremental as it builds on existing bootstrap-based methods.
The paper tackles the problem of combining probabilistic models from distributed or privacy-preserving learning into a single efficient estimator, proposing variance reduction methods to correct bootstrap noise, with theoretical and empirical analysis showing improved performance.
In distributed, or privacy-preserving learning, we are often given a set of probabilistic models estimated from different local repositories, and asked to combine them into a single model that gives efficient statistical estimation. A simple method is to linearly average the parameters of the local models, which, however, tends to be degenerate or not applicable on non-convex models, or models with different parameter dimensions. One more practical strategy is to generate bootstrap samples from the local models, and then learn a joint model based on the combined bootstrap set. Unfortunately, the bootstrap procedure introduces additional noise and can significantly deteriorate the performance. In this work, we propose two variance reduction methods to correct the bootstrap noise, including a weighted M-estimator that is both statistically efficient and practically powerful. Both theoretical and empirical analysis is provided to demonstrate our methods.