Personalized Federated Learning (FL) faces many challenges such as expensive communication costs, training-time adversarial attacks, and performance unfairness across devices. Recent developments witness a trade-off between a reference model and local models to achieve personalization. Following the avenue, we propose a personalized FL method toward the three goals. When it is time to communicate, our method projects local models into a shared-and-fixed low-dimensional random subspace and uses infimal convolution to control the deviation between the reference model and projected local models. We theoretically show our method converges for both strongly convex and non-convex but smooth objectives with square regularizers and the convergence dependence on the projection dimension is mild. We also illustrate the benefits of robustness and fairness on a class of linear problems. Finally, we conduct a large number of experiments to show the empirical superiority of our method over several state-of-the-art methods on the three aspects.

We study Q-learning with Polyak-Ruppert averaging (a.k.a., averaged Q-learning) in a discounted markov decision process in synchronous and tabular settings. Under a Lipschitz condition, we establish a functional central limit theorem for the averaged iteration $\bar{\mathbf{Q}}_T$ and show that its standardized partial-sum process converges weakly to a rescaled Brownian motion. The FCLT implies a fully online inference method for reinforcement learning. Furthermore, we show that $\bar{\mathbf{Q}}_T$ is the regular asymptotically linear (RAL) estimator for the optimal Q-value function $\mathbf{Q}^*$ that has the most efficient influence function. We present a nonasymptotic analysis for the $\ell_{\infty}$ error, $\mathbb{E}\|\bar{\mathbf{Q}}_T-\mathbf{Q}^*\|_{\infty}$, showing that it matches the instance-dependent lower bound for polynomial step sizes. Similar results are provided for entropy-regularized Q-Learning without the Lipschitz condition.

We analyze the novel Local SGD in federated Learning, a multi-round estimation procedure that uses intermittent communication to improve communication efficiency. Under a $2{+}\delta$ moment condition on stochastic gradients, we first establish a {\it functional central limit theorem} that shows the averaged iterates of Local SGD converge weakly to a rescaled Brownian motion. We next provide two iterative inference methods: the {\it plug-in} and the {\it random scaling}. Random scaling constructs an asymptotically pivotal statistic for inference by using the information along the whole Local SGD path. Both the methods are communication efficient and applicable to online data. Our results show that Local SGD simultaneously achieves both statistical efficiency and communication efficiency.

In this paper, we consider linearly constrained stochastic approximation problems with federated learning (FL) as a special case. We propose a stochastic approximation algorithm named by LPSA with probabilistic projections to ensure feasibility so that projections are performed with probability $p_n$ at the $n$-th iteration. Considering a specific family of the probability $p_n$ and step size $\eta_n$, we analyze our algorithm from an asymptotic and continuous perspective. Using a novel jump diffusion approximation, we show that the trajectories consisting of properly rescaled last iterates weakly converge to the solution of specific SDEs. By analyzing the SDEs, we identify the asymptotic behaviors of LPSA for different choices of $(p_n, \eta_n)$. We find the algorithm presents an intriguing asymptotic bias-variance trade-off according to the relative magnitude of $p_n$ w.r.t. $\eta_n$. It provides insights on how to choose appropriate $\{(p_n, \eta_n)\}_{n \geq 1}$ to minimize the projection complexity.

Personalized Federated Learning faces many challenges such as expensive communication costs, training-time adversarial attacks, and performance unfairness across devices. Recent developments witness a trade-off between a reference model and local models to achieve personalization. We follow the avenue and propose a personalized FL method towards the three goals. When it is time to communicate, our method projects local models into a shared-and-fixed low-dimensional random subspace and uses infimal convolution to control the deviation between the reference model and projected local models. We theoretically show our method converges for smooth objectives with square regularizers and the convergence dependence on the projection dimension is mild. We also illustrate the benefits of robustness and fairness on a class of linear problems. Finally, we conduct a large number of experiments to show the empirical superiority of our method over several state-of-the-art methods on the three aspects.

We study distributed computing of the truncated singular value decomposition (SVD). We develop an algorithm that we call \texttt{LocalPower} for improving communication efficiency. Specifically, we uniformly partition the dataset among $m$ nodes and alternate between multiple (precisely $p$) local power iterations and one global aggregation. In the aggregation, we propose to weight each local eigenvector matrix with orthogonal Procrustes transformation (OPT). As a practical surrogate of OPT, sign-fixing, which uses a diagonal matrix with $\pm 1$ entries as weights, has better computation complexity and stability in experiments. We theoretically show that under certain assumptions \texttt{LocalPower} lowers the required number of communications by a factor of $p$ to reach a constant accuracy. We also show that the strategy of periodically decaying $p$ helps obtain high-precision solutions. We conduct experiments to demonstrate the effectiveness of \texttt{LocalPower}.

Subsampled Newton methods approximate Hessian matrices through subsampling techniques to alleviate the per-iteration cost. Previous results require Ω (d) samples to approximate Hessians, where d is the dimension of data points, making it less practical for high-dimensional data. The situation is deteriorated when d is comparably as large as the number of data points n, which requires to take the whole dataset into account, making subsampling not useful. This paper theoretically justifies the effectiveness of subsampled Newton methods on strongly convex empirical risk minimization with high dimensional data. Specifically, we provably require only Θ˜(deffγ) samples for approximating the Hessian matrices, where deffγ is the γ-ridge leverage and can be much smaller than d as long as nγ ≫ 1. Our theories work for three types of Newton methods: subsampled Netwon, distributed Newton, and proximal Newton.

We propose and study a general framework for regularized Markov decision processes (MDPs) where the goal is to find an optimal policy that maximizes the expected discounted total reward plus a policy regularization term. The extant entropy-regularized MDPs can be cast into our framework. Moreover, under our framework, many regularization terms can bring multi-modality and sparsity, which are potentially useful in reinforcement learning. In particular, we present sufficient and necessary conditions that induce a sparse optimal policy. We also conduct a full mathematical analysis of the proposed regularized MDPs, including the optimality condition, performance error, and sparseness control. We provide a generic method to devise regularization forms and propose off-policy actor critic algorithms in complex environment settings. We empirically analyze the numerical properties of optimal policies and compare the performance of different sparse regularization forms in discrete and continuous environments.