Decentralized optimization algorithms have received much attention due to the recent advances in network information processing. However, conventional decentralized algorithms based on projected gradient descent are incapable of handling high dimensional constrained problems, as the projection step becomes computationally prohibitive to compute. To address this problem, this paper adopts a projection-free optimization approach, a.k.a. the Frank-Wolfe (FW) or conditional gradient algorithm. We first develop a decentralized FW (DeFW) algorithm from the classical FW algorithm. The convergence of the proposed algorithm is studied by viewing the decentralized algorithm as an inexact FW algorithm. Using a diminishing step size rule and letting t be the iteration number, we show that the DeFW algorithm's convergence rate is O(1/t) for convex objectives; is O(1/t 2 ) for strongly convex objectives with the optimal solution in the interior of the constraint set; and is O(1/ √ t) towards a stationary point for smooth but non-convex objectives. We then show that a consensus-based DeFW algorithm meets the above guarantees with two communication rounds per iteration. Furthermore, we demonstrate the advantages of the proposed DeFW algorithm on low-complexity robust matrix completion and communication efficient sparse learning. Numerical results on synthetic and real data are presented to support our findings.

The task of estimating a matrix given a sample of observed entries is known as the matrix completion problem. Most works on matrix completion have focused on recovering an unknown real-valued low-rank matrix from a random sample of its entries. Here, we investigate the case of highly quantized observations when the measurements can take only a small number of values. These quantized outputs are generated according to a probability distribution parametrized by the unknown matrix of interest. This model corresponds, for example, to ratings in recommender systems or labels in multi-class classification. We consider a general, non-uniform, sampling scheme and give theoretical guarantees on the performance of a constrained, nuclear norm penalized maximum likelihood estimator. One important advantage of this estimator is that it does not require knowledge of the rank or an upper bound on the nuclear norm of the unknown matrix and, thus, it is adaptive. We provide lower bounds showing that our estimator is minimax optimal. An efficient algorithm based on lifted coordinate gradient descent is proposed to compute the estimator. A limited Monte-Carlo experiment, using both simulated and real data is provided to support our claims.MSC 2010 subject classifications: Primary 62J02, 62J99; secondary 62H12,60B20.

International audienceWe propose distributed algorithms for high-dimensional sparse optimization. In many applications, the parameter is sparse but high-dimensional. This is pathological for existing distributed algorithms as the latter require an information exchange stage involving transmission of the full parameter, which may not be sparse during the intermediate steps of optimization. The novelty of this work is to develop communication efficient algorithms using the stochastic Frank-Wolfe (sFW) algorithm, where the gradient computation is inexact but controllable. For star network topology, we propose an algorithm with low communication cost and establishes its convergence. The proposed algorithm is then extended to perform decentralized optimization on general network topology. Numerical experiments are conducted to verify our findings