Hardness results for neural network approximation problems
Theoretical Computer Science
A Parallel Approximation Algorithm for the Max Cut Problem on Cubic Graphs
ASIAN '99 Proceedings of the 5th Asian Computing Science Conference on Advances in Computing Science
Hardness Results for Neural Network Approximation Problems
EuroCOLT '99 Proceedings of the 4th European Conference on Computational Learning Theory
On Approximate Learning by Multi-layered Feedforward Circuits
ALT '00 Proceedings of the 11th International Conference on Algorithmic Learning Theory
Sharper Bounds for the Hardness of Prototype and Feature Selection
ALT '00 Proceedings of the 11th International Conference on Algorithmic Learning Theory
Max Cut for Random Graphs with a Planted Partition
Combinatorics, Probability and Computing
On approximate learning by multi-layered feedforward circuits
Theoretical Computer Science - Algorithmic learning theory (ALT 2000)
Approximability Distance in the Space of H-Colourability Problems
CSR '09 Proceedings of the Fourth International Computer Science Symposium in Russia on Computer Science - Theory and Applications
Optimal Incentives for Participation with Type-Dependent Externalities
WINE '09 Proceedings of the 5th International Workshop on Internet and Network Economics
On local search for the generalized graph coloring problem
Operations Research Letters
Hi-index | 0.00 |
We study the Max k-Cut problem and its dual, the Min k-Partition problem. In the Min k-Partition problem, given a graph G=(V,E) and positive edge weights, we want to find an edge set of minimum weight whose removal makes G k-colorable. For the Max k-Cut problem we show that, if P!=NP, no polynomial time approximation algorithm can achieve a relative error better than (1/34)k. It is well known that a relative error of 1/k is obtained by a naive randomized heuristic. For the Min k-Partition problem, we show that for k