In the last few years, various communication compression techniques have emerged as an indispensable tool helping to alleviate the communication bottleneck in distributed learning. However, despite the fact biased compressors often show superior performance in practice when compared to the much more studied and understood unbiased compressors, very little is known about them. In this work we study three classes of biased compression operators, two of which are new, and their performance when applied to (stochastic) gradient descent and distributed (stochastic) gradient descent. We show for the first time that biased compressors can lead to linear convergence rates both in the single node and distributed settings. Our distributed SGD method enjoys the ergodic rate Kµ, where δ is a compression parameter which grows when more compression is applied, L and µ are the smoothness and strong convexity constants, C captures stochastic gradient noise (C = 0 if full gradients are computed on each node) and D captures the variance of the gradients at the optimum (D = 0 for over-parameterized models). Further, via a theoretical study of several synthetic and empirical distributions of communicated gradients, we shed light on why and by how much biased compressors outperform their unbiased variants. Finally, we propose a new highly performing biased compressor-combination of Top-k and natural dithering-which in our experiments outperforms all other compression techniques.

Inspired by recent work of Islamov et al (2021), we propose a family of Federated Newton Learn (FedNL) methods, which we believe is a marked step in the direction of making second-order methods applicable to FL. In contrast to the aforementioned work, FedNL employs a different Hessian learning technique which i) enhances privacy as it does not rely on the training data to be revealed to the coordinating server, ii) makes it applicable beyond generalized linear models, and iii) provably works with general contractive compression operators for compressing the local Hessians, such as Top-K or Rank-R, which are vastly superior in practice. Notably, we do not need to rely on error feedback for our methods to work with contractive compressors.Moreover, we develop FedNL-PP, FedNL-CR and FedNL-LS, which are variants of FedNL that support partial participation, and globalization via cubic regularization and line search, respectively, and FedNL-BC, which is a variant that can further benefit from bidirectional compression of gradients and models, i.e., smart uplink gradient and smart downlink model compression.We prove local convergence rates that are independent of the condition number, the number of training data points, and compression variance. Our communication efficient Hessian learning technique provably learns the Hessian at the optimum.Finally, we perform a variety of numerical experiments that show that our FedNL methods have state-of-the-art communication complexity when compared to key baselines.

Abstract. We define λ(r)-convergence, which is a generalization of nontangential convergence in the unit disc. We prove Fatou-type theorems on almost everywhere nontangential convergence of Poisson-Stiltjes integrals for general kernels {ϕr}, forming an approximation of identity. We prove that the bound lim sup r→1 λ(r) ϕr ∞ < ∞ is necessary and sufficient for almost everywhere λ(r)-convergence of the integrals T ϕr(t − x)dµ(t).

In order to mitigate the high communication cost in distributed and federated learning, various vector compression schemes, such as quantization, sparsification and dithering, have become very popular. In designing a compression method, one aims to communicate as few bits as possible, which minimizes the cost per communication round, while at the same time attempting to impart as little distortion (variance) to the communicated messages as possible, which minimizes the adverse effect of the compression on the overall number of communication rounds. However, intuitively, these two goals are fundamentally in conflict: the more compression we allow, the more distorted the messages become. We formalize this intuition and prove an uncertainty principle for randomized compression operators, thus quantifying this limitation mathematically, and effectively providing asymptotically tight lower bounds on what might be achievable with communication compression. Motivated by these developments, we call for the search for the optimal compression operator. In an attempt to take a first step in this direction, we consider an unbiased compression method inspired by the Kashin representation of vectors, which we call Kashin compression (KC). In contrast to all previously proposed compression mechanisms, KC enjoys a dimension independent variance bound for which we derive an explicit formula even in the regime when only a few bits need to be communicate per each vector entry.

No abstract