We propose and study Sparse Polyak, a variant of Polyak’s adaptive step size, designed to solve high-dimensional statistical estimation problems where the problem dimension is allowed to grow much faster than the sample size. In such settings, the standard Polyak step size performs poorly, requiring an increasing number of iterations to achieve optimal statistical precision-even when, the problem remains well conditioned and/or the achievable precision itself does not degrade with problem size. We trace this limitation to a mismatch in how smoothness is measured: in high dimensions, it is no longer effective to estimate the Lipschitz smoothness constant. Instead, it is more appropriate to estimate the smoothness restricted to specific directions relevant to the problem (restricted Lipschitz smoothnes constant). Sparse Polyak overcomes this issue by modifying the step size to estimate the restricted Lipschitz smoothness constant. We support our approach with both theoretical analysis and numerical experiments, demonstrating its improved performance.

We study sparse linear regression over a network of agents, modeled as an undirected graph without a center node. The estimation of the $s$-sparse parameter is formulated as a constrained LASSO problem wherein each agent owns a subset of the $N$ total observations. We analyze the convergence rate and statistical guarantees of a distributed projected gradient tracking-based algorithm under high-dimensional scaling, allowing the ambient dimension $d$ to grow with (and possibly exceed) the sample size $N$. Our theory shows that, under standard notions of restricted strong convexity and smoothness of the average loss functions, suitable conditions on the network connectivity and algorithm tuning, the distributed algorithm converges globally at a linear rate to an estimate that is within the centralized statistical precision of the model, $O(s\log d/N)$. When $s\log d/N=o(1)$, a condition necessary for statistical consistency, an $\varepsilon$-optimal solution is attained after ${O}(\kappa \log (1/\varepsilon))$ gradient computations and $O(\kappa/(1-\rho) \log (1/\varepsilon))$ communication rounds, where $\kappa$ is the restricted condition number of the loss function and $\rho$ measures the network connectivity. The computation cost matches that of the centralized projected gradient algorithm despite having data distributed; whereas the communication rounds reduce as the network connectivity improves. Overall, our study reveals interesting connections between statistical efficiency, network connectivity and topology, and convergence rate in the high dimensional setting.

We explore the matrix sensing problem from near-isotropic linear measurements, distributed across a network of agents modeled as an undirected graph, with no centralized node. We provide the first study of statistical, computational/communication guarantees for a decentralized gradient algorithm that solves the (nonconvex) Burer-Monteiro type decomposition associated to the low-rank matrix estimation. With small random initialization, the algorithm displays an approximate two-phase convergence: (i) a spectral phase that aligns the iterates' column space with the underlying low-rank matrix, mimicking centralized spectral initialization (not directly implementable over networks); and (ii) a local refinement phase that diverts the iterates from certain degenerate saddle points, while ensuring swift convergence to the underlying low-rank matrix. Central to our analysis is a novel "in-network" Restricted Isometry Property which accommodates for the decentralized nature of the optimization, revealing an intriguing interplay between sample complexity and network connectivity, topology, and communication complexity.

We study linear regression from data distributed over a network of agents (with no master node) under high-dimensional scaling, which allows the ambient dimension to grow faster than the sample size. We propose a novel decentralization of the projected gradient algorithm whereby agents iteratively update their local estimates by a “double-mixing” mechanism, which suitably combines averages of iterates and gradients of neighbouring nodes. Under standard assumptions on the statistical model and network connectivity, the proposed method enjoys global linear convergence up to the statistical precision of the model. This improves on guarantees of (plain) DGD algorithms, whose iteration complexity grows undesirably with the ambient dimension. Our technical contribution is a novel convergence analysis that resembles (albeit different) algorithmic stability arguments extended to high-dimensions and distributed setting, which is of independent interest.

We study acceleration for distributed sparse regression in {\it high-dimensions}, which allows the parameter size to exceed and grow faster than the sample size. When applicable, existing distributed algorithms employing acceleration perform poorly in this setting, theoretically and numerically. We propose a new accelerated distributed algorithm suitable for high-dimensions. The method couples a suitable instance of accelerated Nesterov's proximal gradient with consensus and gradient-tracking mechanisms, aiming at estimating locally the gradient of the empirical loss while enforcing agreement on the local estimates. Under standard assumptions on the statistical model and tuning parameters, the proposed method is proved to globally converge at {\it linear} rate to an estimate that is within the {\it statistical precision} of the model. The iteration complexity scales as $\mathcal{O}(\sqrt{\kappa})$, while the communications per iteration are at most $\widetilde{\mathcal{O}}(\log m/(1-\rho))$, where $\kappa$ is the restricted condition number of the empirical loss, $m$ is the number of agents, and $\rho\in (0,1)$ measures the network connectivity. As by-product of our design, we also report an accelerated method for high-dimensional estimations over master-worker architectures, which is of independent interest and compares favorably with existing works.

In this paper we consider distributed convex optimization over time-varying undirected graphs. We propose a linearized version of primarily averaged network dual ascent (PANDA) that keeps the advantages of PANDA while requiring less computational costs. The proposed method, economic primarily averaged network dual ascent (Eco-PANDA), provably converges at R-linear rate to the optimal point given that the agents' objective functions are strongly convex and have Lipschitz continuous gradients. Therefore, the method is competitive, in terms of type of rate, with both DIGing and PANDA. The proposed method halves the communication costs of methods like DIGing while still converging R-linearly and having the same per iterate complexity.