Recursion-Free Online Multiple Incremental/Decremental Analysis Based on Ridge Support Vector Learning
This work addresses efficiency issues in online learning for machine learning practitioners, though it appears incremental as it builds on prior Ridge Support Vector Models.
The paper tackles the problem of slow incremental and decremental updates in support vector machines by introducing a recursion-free mechanism based on Weight-Error Curves, which computes all new Lagrangian multipliers at once without gradual steps, eliminating the need for bookkeeping strategies that check all training samples per round.
This study presents a rapid multiple incremental and decremental mechanism based on Weight-Error Curves (WECs) for support-vector analysis. Recursion-free computation is proposed for predicting the Lagrangian multipliers of new samples. This study examines Ridge Support Vector Models, subsequently devising a recursion-free function derived from WECs. With the proposed function, all the new Lagrangian multipliers can be computed at once without using any gradual step sizes. Moreover, such a function relaxes a constraint, where the increment of new multiple Lagrangian multipliers should be the same in the previous work, thereby easily satisfying the requirement of KKT conditions. The proposed mechanism no longer requires typical bookkeeping strategies, which compute the step size by checking all the training samples in each incremental round.