Random algorithms for convex minimization problems

This paper deals with iterative gradient and subgradient methods with random feasibility steps for solving constrained convex minimization problems, where the constraint set is specified as the intersection of possibly infinitely many constraint sets. Each constraint set is assumed to be given as a level set of a convex but not necessarily differentiable function. The proposed algorithms are applicable to the situation where the whole constraint set of the problem is not known in advance, but it is rather learned in time through observations. Also, the algorithms are of interest for constrained optimization problems where the constraints are known but the number of constraints is either large or not finite. We analyze the proposed algorithm for the case when the objective function is differentiable with Lipschitz gradients and the case when the objective function is not necessarily differentiable. The behavior of the algorithm is investigated both for diminishing and non-diminishing stepsize values. The almost sure convergence to an optimal solution is established for diminishing stepsize. For non-diminishing stepsize, the error bounds are established for the expected distances of the weighted averages of the iterates from the constraint set, as well as for the expected sub-optimality of the function values along the weighted averages.

[1]  Frank Deutsch,et al.  The rate of convergence for the cyclic projections algorithm I: Angles between convex sets , 2006, J. Approx. Theory.

[2]  Krzysztof C. Kiwiel,et al.  Convergence of Approximate and Incremental Subgradient Methods for Convex Optimization , 2003, SIAM J. Optim..

[3]  Marc Teboulle,et al.  Gradient-based algorithms with applications to signal-recovery problems , 2010, Convex Optimization in Signal Processing and Communications.

[4]  Boris Polyak.  Minimization of unsmooth functionals , 1969 .

[5]  Angelia Nedic,et al.  Incremental Stochastic Subgradient Algorithms for Convex Optimization , 2008, SIAM J. Optim..

[6]  Heinz H. Bauschke,et al.  Projection algorithms and monotone operators , 1996 .

[7]  Luo Zhi-quan,et al.  Analysis of an approximate gradient projection method with applications to the backpropagation algorithm , 1994 .

[8]  Yuri Ermoliev,et al.  Stochastic quasigradient methods. Numerical techniques for stochastic optimization , 1988 .

[9]  J. Burkey,et al.  WEAK SHARP MINIMA IN MATHEMATICAL PROGRAMMING , 1993 .

[10]  F. Facchinei,et al.  Finite-Dimensional Variational Inequalities and Complementarity Problems , 2003 .

[11]  Marc Teboulle,et al.  A Fast Iterative Shrinkage-Thresholding Algorithm for Linear Inverse Problems , 2009, SIAM J. Imaging Sci..

[12]  Frank Deutsch,et al.  The rate of convergence for the cyclic projections algorithm II: Norms of nonlinear operators , 2006, J. Approx. Theory.

[13]  Andrzej Cegielski,et al.  Relaxed Alternating Projection Methods , 2008, SIAM J. Optim..

[14]  D. Bertsekas,et al.  A hybrid incremental gradient method for least squares problems , 1994 .

[15]  Frank Deutsch,et al.  The rate of convergence for the cyclic projections algorithm III: Regularity of convex sets , 2008, J. Approx. Theory.

[16]  N. Aronszajn.  Theory of Reproducing Kernels. , 1950 .

[17]  Heinz H. Bauschke,et al.  Hybrid projection-reflection method for phase retrieval. , 2003, Journal of the Optical Society of America. A, Optics, image science, and vision.

[18]  V. Borkar.  Stochastic Approximation: A Dynamical Systems Viewpoint , 2008 .

[19]  Dimitri P. Bertsekas,et al.  Incremental proximal methods for large scale convex optimization , 2011, Math. Program..

[20]  A. Banerjee.  Convex Analysis and Optimization , 2006 .

[21]  Rajeev Agrawal,et al.  Joint scheduling and resource allocation in uplink OFDM systems for broadband wireless access networks , 2009, IEEE Journal on Selected Areas in Communications.

[22]  F. Deutsch.  Rate of Convergence of the Method of Alternating Projections , 1984 .

[23]  Yuri Ermoliev,et al.  Stochastic Programming Methods , 1976 .

[24]  Leandros Tassiulas,et al.  Resource Allocation and Cross Layer Control in Wireless Networks (Foundations and Trends in Networking, V. 1, No. 1) , 2006 .

[25]  R. Srikant,et al.  Fair resource allocation in wireless networks using queue-length-based scheduling and congestion control , 2007, TNET.

[26]  Yuri Ermoliev,et al.  Numerical techniques for stochastic optimization , 1988 .

[27]  Boris Polyak.  Random Algorithms for Solving Convex Inequalities , 2001 .

[28]  Patrick L. Combettes,et al.  A Convex Programming Algorithm for Noisy Discrete Tomography , 2007 .

[29]  Paul Tseng,et al.  An Incremental Gradient(-Projection) Method with Momentum Term and Adaptive Stepsize Rule , 1998, SIAM J. Optim..

[30]  G. Duclos.  New York 1987 , 2000 .

[31]  Boris Polyak,et al.  The method of projections for finding the common point of convex sets , 1967 .

[32]  A. Kruger,et al.  Error Bounds: Necessary and Sufficient Conditions , 2010 .

[33]  James V. Burke,et al.  A Unified Analysis of Hoffman's Bound via Fenchel Duality , 1996, SIAM J. Optim..

[34]  John N. Tsitsiklis,et al.  Gradient Convergence in Gradient methods with Errors , 1999, SIAM J. Optim..

[35]  Y. Ermoliev.  Stochastic quasigradient methods and their application to system optimization , 1983 .

[36]  Olvi L. Mangasarian.  Error bounds for nondifferentiable convex inequalities under a strong Slater constraint qualification , 1998, Math. Program..

[37]  G. Herman,et al.  Advances in discrete tomography and its applications , 2007 .

[38]  Patrick L. Combettes,et al.  Convex set theoretic image recovery by extrapolated iterations of parallel subgradient projections , 1997, IEEE Trans. Image Process..

[39]  Mikhail V. Solodov,et al.  Incremental Gradient Algorithms with Stepsizes Bounded Away from Zero , 1998, Comput. Optim. Appl..

[40]  Zhi-Quan Luo,et al.  New error bounds and their applications to convergence analysis of iterative algorithms , 2000, Math. Program..

[41]  P. Tseng.  Successive Projection under a Quasi-Cyclic Order , 1990 .

[42]  K. Knopp,et al.  Theory and Applications of Infinite Series , 1972 .

[43]  D. Bertsekas.  Gradient convergence in gradient methods , 1997 .

[44]  Heinz H. Bauschke,et al.  On Projection Algorithms for Solving Convex Feasibility Problems , 1996, SIAM Rev..

[45]  Dimitri P. Bertsekas,et al.  A New Class of Incremental Gradient Methods for Least Squares Problems , 1997, SIAM J. Optim..

[46]  A. Lewis,et al.  Error Bounds for Convex Inequality Systems , 1998 .

[47]  T. M. Williams,et al.  Optimizing Methods in Statistics , 1981 .

[48]  Yonina C. Eldar,et al.  Convex Optimization in Signal Processing and Communications , 2009 .

[49]  Heinz H. Bauschke.  Projection Algorithms: Results and Open Problems , 2001 .

[50]  Leandros Tassiulas,et al.  Resource Allocation and Cross-Layer Control in Wireless Networks , 2006, Found. Trends Netw..

[51]  H. Robbins,et al.  A CONVERGENCE THEOREM FOR NON NEGATIVE ALMOST SUPERMARTINGALES AND SOME APPLICATIONS**Research supported by NIH Grant 5-R01-GM-16895-03 and ONR Grant N00014-67-A-0108-0018. , 1971 .

[52]  Yurii Nesterov,et al.  Smooth minimization of non-smooth functions , 2005, Math. Program..

[53]  Dimitri P. Bertsekas,et al.  A Note on Error Bounds for Convex and Nonconvex Programs , 1999, Comput. Optim. Appl..

[54]  O. Nelles,et al.  An Introduction to Optimization , 1996, IEEE Antennas and Propagation Magazine.

[55]  Alexander L. Stolyar,et al.  On the Asymptotic Optimality of the Gradient Scheduling Algorithm for Multiuser Throughput Allocation , 2005, Oper. Res..

[56]  Dimitri P. Bertsekas,et al.  Incremental Subgradient Methods for Nondifferentiable Optimization , 2001, SIAM J. Optim..