Differentially Quantized Gradient Methods
This addresses communication efficiency in distributed machine learning, offering a method to eliminate quantization loss for smooth, strongly convex problems, though it is incremental as it builds on existing gradient methods.
The paper tackles the problem of distributed optimization with rate-limited communication by introducing Differential Quantization (DQ), which compensates past quantization errors to align quantized and unquantized gradient descent trajectories. It proves that DQ-GD achieves a linear contraction factor matching unquantized GD when the bitrate exceeds a threshold, with no loss due to quantization, and shows asymptotic optimality in high dimensions.
Consider the following distributed optimization scenario. A worker has access to training data that it uses to compute the gradients while a server decides when to stop iterative computation based on its target accuracy or delay constraints. The server receives all its information about the problem instance from the worker via a rate-limited noiseless communication channel. We introduce the principle we call Differential Quantization (DQ) that prescribes compensating the past quantization errors to direct the descent trajectory of a quantized algorithm towards that of its unquantized counterpart. Assuming that the objective function is smooth and strongly convex, we prove that Differentially Quantized Gradient Descent (DQ-GD) attains a linear contraction factor of $\max\{σ_{\mathrm{GD}}, ρ_n 2^{-R}\}$, where $σ_{\mathrm{GD}}$ is the contraction factor of unquantized gradient descent (GD), $ρ_n \geq 1$ is the covering efficiency of the quantizer, and $R$ is the bitrate per problem dimension $n$. Thus at any $R\geq\log_2 ρ_n /σ_{\mathrm{GD}}$ bits, the contraction factor of DQ-GD is the same as that of unquantized GD, i.e., there is no loss due to quantization. We show that no algorithm within a certain class can converge faster than $\max\{σ_{\mathrm{GD}}, 2^{-R}\}$. Since quantizers exist with $ρ_n \to 1$ as $n \to \infty$ (Rogers, 1963), this means that DQ-GD is asymptotically optimal. The principle of differential quantization continues to apply to gradient methods with momentum such as Nesterov's accelerated gradient descent, and Polyak's heavy ball method. For these algorithms as well, if the rate is above a certain threshold, there is no loss in contraction factor obtained by the differentially quantized algorithm compared to its unquantized counterpart. Experimental results on least-squares problems validate our theoretical analysis.