SEBOOST - Boosting Stochastic Learning Using Subspace Optimization Techniques
This work addresses the challenge of enhancing stochastic learning efficiency for machine learning practitioners, though it appears incremental as it builds on existing optimization methods.
The authors tackled the problem of improving stochastic optimization methods by introducing SEBOOST, a technique that applies secondary subspace optimization between descent steps, which boosted performance and robustness of various algorithms without significantly increasing computational cost.
We present SEBOOST, a technique for boosting the performance of existing stochastic optimization methods. SEBOOST applies a secondary optimization process in the subspace spanned by the last steps and descent directions. The method was inspired by the SESOP optimization method for large-scale problems, and has been adapted for the stochastic learning framework. It can be applied on top of any existing optimization method with no need to tweak the internal algorithm. We show that the method is able to boost the performance of different algorithms, and make them more robust to changes in their hyper-parameters. As the boosting steps of SEBOOST are applied between large sets of descent steps, the additional subspace optimization hardly increases the overall computational burden. We introduce two hyper-parameters that control the balance between the baseline method and the secondary optimization process. The method was evaluated on several deep learning tasks, demonstrating promising results.