Bridging the Gap Between Homogeneous and Heterogeneous Asynchronous Optimization is Surprisingly Difficult

ICLR 2026 Conference Submission17824 Authors

Keywords: parallel and asynchronous methods, lower bounds, homogeneous optimization, heterogeneous optimization

Abstract: Modern large-scale machine learning tasks often require multiple workers, devices, CPUs, or GPUs to compute stochastic gradients in parallel and asynchronously to train model weights. Theoretical results typically distinguish between two settings: (i) the homogeneous setting, where all workers have access to the same data distribution, and (ii) the heterogeneous setting, where each worker operates on different data distributions. Known optimal time complexities in these settings reveal a significant gap, with far more pessimistic guarantees in the heterogeneous case. In this work, we investigate whether these pessimistic optimal time complexities can be overcome under different assumptions. Surprisingly, we show that improvement is provably impossible under widely used first- and second-order similarity assumptions for a broad family of algorithms. We then turn to the interpolation regime and demonstrate that the weak interpolation assumption alone is also insufficient. Finally, we introduce a minimal combination of irreducible assumptions, strong interpolation and the local Polyak-Lojasiewicz condition, to derive a new time complexity bound that matches the best-known result in the homogeneous setting, without requiring identical data distributions.

Primary Area: optimization

Submission Number: 17824