Communication Efficient Distributed Agnostic Boosting
This work addresses the challenge of efficient and robust distributed learning for applications handling noisy data, representing a significant but incremental advance over existing methods.
The paper tackles the problem of learning from distributed data with arbitrary noise by introducing a distributed boosting-based procedure that is noise tolerant, communication efficient, and computationally efficient, improving over prior works that were limited to noise-free scenarios or computationally prohibitive methods.
We consider the problem of learning from distributed data in the agnostic setting, i.e., in the presence of arbitrary forms of noise. Our main contribution is a general distributed boosting-based procedure for learning an arbitrary concept space, that is simultaneously noise tolerant, communication efficient, and computationally efficient. This improves significantly over prior works that were either communication efficient only in noise-free scenarios or computationally prohibitive. Empirical results on large synthetic and real-world datasets demonstrate the effectiveness and scalability of the proposed approach.