A simple polynomial-time rescaling algorithm for solving linear programs

The perceptron algorithm, developed mainly in the machine learning literature, is a simple greedy method for finding a feasible solution to a linear program (alternatively, for learning a threshold function). In spite of its exponential worst-case complexity, it is often quite useful, in part due to its noise-tolerance and also its overall simplicity. In this paper, we show that a randomized version of the perceptron algorithm along with periodic rescaling runs in polynomial-time. The resulting algorithm for linear programming has an elementary description and analysis.

[1]  N. Z. Shor.  Cut-off method with space extension in convex programming problems , 1977, Cybernetics.

[2]  Narendra Karmarkar,et al.  A new polynomial-time algorithm for linear programming , 1984, Comb..

[3]  Jürgen Forster.  A linear lower bound on the unbounded error probabilistic communication complexity , 2002, J. Comput. Syst. Sci..

[4]  Tom Bylander,et al.  Learning linear threshold functions in the presence of classification noise , 1994, COLT '94.

[5]  Robert M. Freund,et al.  Interior point methods : current status and future directions , 1996 .

[6]  S. Agmon.  The Relaxation Method for Linear Inequalities , 1954, Canadian Journal of Mathematics.

[7]  L. Lovász,et al.  Geometric Algorithms and Combinatorial Optimization , 1981 .

[8]  Alan M. Frieze,et al.  A Polynomial-Time Algorithm for Learning Noisy Linear Threshold Functions , 1996, Algorithmica.

[9]  Santosh S. Vempala,et al.  Solving convex programs by random walks , 2004, JACM.

[10]  A. A. Mullin,et al.  Principles of neurodynamics , 1962 .

[11]  N. Z. Shor.  Utilization of the operation of space dilatation in the minimization of convex functions , 1972 .

[12]  Rocco A. Servedio,et al.  Perceptron, Winnow, and PAC Learning , 2002, SIAM J. Comput..

[13]  Jean-Louis Goffin,et al.  The Relaxation Method for Solving Systems of Linear Inequalities , 1980, Math. Oper. Res..

[14]  Rocco A. Servedio,et al.  Smooth Boosting and Learning with Malicious Noise , 2001, J. Mach. Learn. Res..

[15]  James Renegar,et al.  Incorporating Condition Measures into the Complexity Theory of Linear Programming , 1995, SIAM J. Optim..

[16]  Felipe Cucker,et al.  A new condition number for linear programming , 2001, Math. Program..

[17]  Robert M. Freund,et al.  Some characterizations and properties of the “distance to ill-posedness” and the condition measure of a conic linear system , 1999, Math. Program..

[18]  John Dunagan,et al.  Smoothed analysis of the perceptron algorithm for linear programming , 2002, SODA '02.

[19]  Pravin M. Vaidya,et al.  A new algorithm for minimizing convex functions over convex sets , 1996, Math. Program..

[20]  D. Spielman,et al.  Smoothed Analysis of Renegar’s Condition Number for Linear Programming , 2002 .

[21]  Edith Cohen,et al.  Learning noisy perceptrons by a perceptron in polynomial time , 1997, Proceedings 38th Annual Symposium on Foundations of Computer Science.