Author

Robert W. Heath

2 papers indexed here

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

Conference May 2026

Variance-Reduced Q-Learning over Static and Time-Varying Networks

It is proved that such speedups in sample-complexity require only $\tilde O\left( 1 \right)$ communication, substantially improving upon the communication costs in prior work.

Sreejeet Maity, Feng Zhu, Aritra Mitra et al. · American Control Conference · 0 citations

#machine learning Preprint Sep 2026

High-Probability Convergence of SGD via Batched Updates

This work proposes Batched SGD, a simple variant that partitions online samples into epochs and performs a single update per epoch using a refined, low-variance gradient estimate, and provides the first high-probability guarantees for FL.

Feng Zhu, Robert W. Heath, Aritra Mitra · 0 citations