Please help transcribe this video using our simple transcription tool. You need to be logged in to do so.


We consider a suboptimal solution path algorithm for the Support Vector Machine. The solution path algorithm is known as an effective tool for solving a sequence of a parametrized optimization problems in machine learning. However, the algorithm needs to keep strict optimality conditions satisfied everywhere on the path. This requirement narrows the applicability of the path algorithm and adversely affects its computational efficiency. In our algorithm, user can specify tolerances to the optimality and control the trade-off between accuracy of the solution and the computational cost. We also show that our suboptimal solutions can be interpreted as the solution of a perturbed optimization problem from the original one, provide some theoretical analyses of our algorithm based on a novel interpretation. The experimental results demonstrate the effectiveness of our algorithm in terms of efficiency and accuracy.

Questions and Answers

You need to be logged in to be able to post here.