Exponential Quantum Communication Advantage in Distributed Learning

Training and inference with large machine learning models that far exceed the memory capacity of individual devices necessitates the design of distributed architectures, forcing one to contend with communication constraints. We present a framework for distributed computation over a quantum network in which data is encoded into specialized quantum states. We prove that for certain models within this framework, inference and training using gradient descent can be performed with exponentially less communication compared to their classical analogs, and with relatively modest time and space complexity overheads relative to standard gradient-based methods. To our knowledge, this is the first example of exponential quantum advantage for a generic class of machine learning problems with dense classical data that holds regardless of the data encoding cost. Moreover, we show that models in this class can encode highly nonlinear features of their inputs, and their expressivity increases exponentially with model depth. We also find that, interestingly, the communication advantage nearly vanishes for simpler linear classifiers. These results can be combined with natural privacy advantages in the communicated quantum states that limit the amount of information that can be extracted from them about the data and model parameters. Taken as a whole, these findings form a promising foundation for distributed machine learning over quantum networks.