Adaptive Data Fusion for Multi-task Non-smooth Optimization
This addresses sample efficiency in multi-task optimization for statistical learning and decision-making, but appears incremental as it builds on existing data fusion methods.
The paper tackles multi-task non-smooth optimization by developing an adaptive data fusion approach that leverages commonalities among objectives to improve sample efficiency, with numerical experiments showing significant advantages over benchmarks.
We study the problem of multi-task non-smooth optimization that arises ubiquitously in statistical learning, decision-making and risk management. We develop a data fusion approach that adaptively leverages commonalities among a large number of objectives to improve sample efficiency while tackling their unknown heterogeneities. We provide sharp statistical guarantees for our approach. Numerical experiments on both synthetic and real data demonstrate significant advantages of our approach over benchmarks.