Binary Matrix Guessing Problem
This work addresses a specific matrix problem, but it is incremental as it combines existing methods without broad impact.
The paper tackles the Binary Matrix Guessing Problem by introducing two algorithms: the fast Elementwise Probing Algorithm and the slower but more general Additive Reinforcement Learning Algorithm, with computational performance comparisons and numerical results provided.
We introduce the Binary Matrix Guessing Problem and provide two algorithms to solve this problem. The first algorithm we introduce is Elementwise Probing Algorithm (EPA) which is very fast under a score which utilizes Frobenius Distance. The second algorithm is Additive Reinforcement Learning Algorithm which combines ideas from perceptron algorithm and reinforcement learning algorithm. This algorithm is significantly slower compared to first one, but less restrictive and generalizes better. We compare computational performance of both algorithms and provide numerical results. reason for withdrawal: Paper will be rewritten with experiments replicated on verified and validated hardware and software.