Learning and Intelligent Optimization

We propose accelerated randomized coordinate descent algorithms for stochastic optimization and online learning. Our algorithms have significantly less per-iteration complexity than the known accelerated gradient algorithms. The proposed algorithms for online learning have better regret performance than the known randomized online coordinate descent algorithms. Furthermore, the proposed algorithms for stochastic optimization exhibit as good convergence rates as the best known randomized coordinate descent algorithms. We also show simulation results to demonstrate performance of the proposed algorithms.

[1]  Nils J. Nilsson,et al.  A Formal Basis for the Heuristic Determination of Minimum Cost Paths , 1968, IEEE Trans. Syst. Sci. Cybern..

[2]  David Maier,et al.  The Complexity of Some Problems on Subsequences and Supersequences , 1978, JACM.

[3]  Mike Paterson,et al.  A Faster Algorithm Computing String Edit Distances , 1980, J. Comput. Syst. Sci..

[4]  Inyong Ham,et al.  A heuristic algorithm for the m-machine, n-job flow-shop sequencing problem , 1983 .

[5]  James A. Storer,et al.  Data Compression: Methods and Theory , 1987 .

[6]  P. Ow,et al.  Filtered beam search in scheduling , 1988 .

[7]  Éric D. Taillard,et al.  Benchmarks for basic scheduling problems , 1993 .

[8]  Cameron Bruce Fraser,et al.  Subsequences and Supersequences of Strings , 1995 .

[9]  Kanagasabai Rajaraman,et al.  Finite time analysis of the pursuit algorithm for learning automata , 1996, IEEE Trans. Syst. Man Cybern. Part B.

[10]  Dan Gusfield.  Algorithms on Strings, Trees, and Sequences - Computer Science and Computational Biology , 1997 .

[11]  L. Bergroth,et al.  A survey of longest common subsequence algorithms , 2000, Proceedings Seventh International Symposium on String Processing and Information Retrieval. SPIRE 2000.

[12]  Paola Bonizzoni,et al.  Experimenting an approximation algorithm for the LCS , 2001, Discret. Appl. Math..

[13]  Helena Ramalhinho Dias Lourenço,et al.  Iterated Local Search , 2001, Handbook of Metaheuristics.

[14]  Bin Ma,et al.  A General Edit Distance between RNA Structures , 2002, J. Comput. Biol..

[15]  M. Giel-Pietraszuk,et al.  Palindromes in Proteins , 2003, Journal of protein chemistry.

[16]  Majid Sarrafzadeh,et al.  Area-efficient instruction set synthesis for reconfigurable system-on-chip designs , 2004, Proceedings. 41st Design Automation Conference, 2004..

[17]  Thomas Stützle,et al.  Pareto Local Optimum Sets in the Biobjective Traveling Salesman Problem: An Experimental Study , 2004, Metaheuristics for Multiobjective Optimisation.

[18]  Chang-Biau Yang,et al.  Fast Algorithms for Finding the Common Subsequence of Multiple Sequences , 2004 .

[19]  Dirk Thierens,et al.  An Adaptive Pursuit Strategy for Allocating Operator Probabilities , 2005, BNAIC.

[20]  Mehryar Mohri,et al.  Multi-armed Bandit Algorithms and Empirical Evaluation , 2005, ECML.

[21]  Richard S. Sutton,et al.  Reinforcement Learning: An Introduction , 1998, IEEE Trans. Neural Networks.

[22]  Charles Q. Choi.  DNA palindromes found in cancer , 2005, Genome Biology.

[23]  David Pisinger,et al.  An Adaptive Large Neighborhood Search Heuristic for the Pickup and Delivery Problem with Time Windows , 2006, Transp. Sci..

[24]  S. Larionov,et al.  Chromosome evolution with naked eye: palindromic context of the life origin. , 2008, Chaos.

[25]  Manuel López-Ibáñez,et al.  Beam search for the longest common subsequence problem , 2009, Comput. Oper. Res..

[26]  Kate Smith-Miles,et al.  Cross-disciplinary perspectives on meta-learning for algorithm selection , 2009, CSUR.

[27]  Patrick De Causmaecker,et al.  Learning agents for the multi-mode project scheduling problem , 2011, J. Oper. Res. Soc..

[28]  Sayyed Rasoul Mousavi,et al.  An improved algorithm for the longest common subsequence problem , 2012, Comput. Oper. Res..

[29]  Thomas Stützle,et al.  Automatic Design of Hybrid Stochastic Local Search Algorithms , 2013, Hybrid Metaheuristics.

[30]  Shihabur Rahman Chowdhury,et al.  Computing a Longest Common Palindromic Subsequence , 2014, Fundam. Informaticae.

[31]  Graham Kendall,et al.  A Dynamic Multiarmed Bandit-Gene Expression Programming Hyper-Heuristic for Combinatorial Optimization Problems , 2015, IEEE Transactions on Cybernetics.

[32]  Leslie Pérez Cáceres,et al.  The irace package: Iterated racing for automatic algorithm configuration , 2016 .

[33]  Christian Blum,et al.  Hybrid Metaheuristics: Powerful Tools for Optimization , 2016 .

[34]  C. Blum,et al.  Longest Common Subsequence Problems , 2016 .

[35]  Md. Mahbubul Hasan,et al.  Palindromic Subsequence Automata and Longest Common Palindromic Subsequence , 2017, Math. Comput. Sci..

[36]  Shunsuke Inenaga,et al.  A hardness result and new algorithm for the longest common palindromic subsequence problem , 2016, Inf. Process. Lett..