Search

In this paper, we propose a first second-order scheme based on arbitrary non-Euclidean norms, incorporated by Bregman distances. They are introduced directly in the Newton iterate with regularization parameter proportional to the square root of the norm of the current gradient. For the basic scheme, as applied to the composite convex optimization problem, we establish the global convergence rate of the order O (k - 2) both in terms of the functional residual and in the norm of subgradients. Our main assumption on the smooth part of the objective is Lipschitz continuity of its Hessian. For uniformly convex functions of degree three, we justify global linear rate, and for strongly convex function we prove the local superlinear rate of convergence. Our approach can be seen as a relaxation of the Cubic Regularization of the Newton method (Nesterov and Polyak in Math Program 108(1):177–205, 2006) for convex minimization problems. This relaxation preserves the convergence properties and global complexities of the Cubic Newton in convex case, while the auxiliary subproblem at each iteration is simpler. We equip our method with adaptive search procedure for choosing the regularization parameter. We propose also an accelerated scheme with convergence rate O (k - 3) , where k is the iteration counter. [ABSTRACT FROM AUTHOR]

In this paper, we focus on solving the decentralized optimization problem of minimizing the sum of n objective functions over a multi-agent network. The agents are embedded in an undirected graph where they can only send/receive information directly to/from their immediate neighbors. Assuming smooth and strongly convex objective functions, we propose an Optimal Gradient Tracking (OGT) method that achieves the optimal gradient computation complexity O κ log 1 ϵ and the optimal communication complexity O κ θ log 1 ϵ simultaneously, where κ and 1 θ denote the condition numbers related to the objective functions and the communication graph, respectively. To our best knowledge, OGT is the first single-loop decentralized gradient-type method that is optimal in both gradient computation and communication complexities. The development of OGT involves two building blocks that are also of independent interest. The first one is another new decentralized gradient tracking method termed "Snapshot" Gradient Tracking (SS-GT), which achieves the gradient computation and communication complexities of O κ log 1 ϵ and O κ θ log 1 ϵ , respectively. SS - G T can be potentially extended to more general settings compared to OGT. The second one is a technique termed Loopless Chebyshev Acceleration (LCA), which can be implemented "looplessly" but achieves a similar effect by adding multiple inner loops of Chebyshev acceleration in the algorithm. In addition to SS - G T , this LCA technique can accelerate many other gradient tracking based methods with respect to the graph condition number 1 θ . [ABSTRACT FROM AUTHOR]

Stochastic (sub)gradient methods require step size schedule tuning to perform well in practice. Classical tuning strategies decay the step size polynomially and lead to optimal sublinear rates on (strongly) convex problems. An alternative schedule, popular in nonconvex optimization, is called geometric step decay and proceeds by halving the step size after every few epochs. In recent work, geometric step decay was shown to improve exponentially upon classical sublinear rates for the class of sharp convex functions. In this work, we ask whether geometric step decay similarly improves stochastic algorithms for the class of sharp weakly convex problems. Such losses feature in modern statistical recovery problems and lead to a new challenge not present in the convex setting: the region of convergence is local, so one must bound the probability of escape. Our main result shows that for a large class of stochastic, sharp, nonsmooth, and nonconvex problems a geometric step decay schedule endows well-known algorithms with a local linear (or nearly linear) rate of convergence to global minimizers. This guarantee applies to the stochastic projected subgradient, proximal point, and prox-linear algorithms. As an application of our main result, we analyze two statistical recovery tasks—phase retrieval and blind deconvolution—and match the best known guarantees under Gaussian measurement models and establish new guarantees under heavy-tailed distributions. [ABSTRACT FROM AUTHOR]

We give a simple and natural method for computing approximately optimal solutions for minimizing a convex function f over a convex set K given by a separation oracle. Our method utilizes the Frank–Wolfe algorithm over the cone of valid inequalities of K and subgradients of f. Under the assumption that f is L-Lipschitz and that K contains a ball of radius r and is contained inside the origin centered ball of radius R, using O (R L) 2 ε 2 · R 2 r 2 iterations and calls to the oracle, our main method outputs a point x ∈ K satisfying f (x) ≤ ε + min z ∈ K f (z) . Our algorithm is easy to implement, and we believe it can serve as a useful alternative to existing cutting plane methods. As evidence towards this, we show that it compares favorably in terms of iteration counts to the standard LP based cutting plane method and the analytic center cutting plane method, on a testbed of combinatorial, semidefinite and machine learning instances. [ABSTRACT FROM AUTHOR]