4 papers · 1 filter
Agile Online Model Selection: Resolving Adaptation Lag via Safeguarded Large Learning Rates
Kei Takemura, Ryuta Matsuno, Keita Sakuma
Maintaining predictive accuracy in non-stationary environments requires online model selection to adapt autonomously to unknown distribution shifts. However, existing tuning-free a…
Source Component Shift Adaptation via Offline Decomposition and Online Mixing Approach
Ryuta Matsuno
This paper addresses source component shift adaptation, aiming to update predictions adapting to source component shifts for incoming data streams based on past training data. Exis…
Improved Impossible Tuning and Lipschitz-Adaptive Universal Online Learning with Gradient Variations
Kei Takemura, Ryuta Matsuno, Keita Sakuma
A central goal in online learning is to achieve adaptivity to unknown problem characteristics, such as environmental changes captured by gradient variation (GV), function curvature…
Backward Compatibility in Attributive Explanation and Enhanced Model Training Method
Ryuta Matsuno
Model update is a crucial process in the operation of ML/AI systems. While updating a model generally enhances the average prediction performance, it also significantly impacts the…