Model-and-search: a derivative-free local optimization algorithm
Sign Up to like & getrecommendations! Published in 2025 at "Computational Optimization and Applications"
DOI: 10.1007/s10589-025-00686-9
Abstract: In this work, we propose Model-and-Search (MAS), a novel local-search derivative-free optimization algorithm, and show that it is convergent to a Karush-Kuhn-Tucker point. MAS aims to optimize a deterministic function over a box-bounded domain and… read more here.
Keywords: search derivative; model search; search; derivative free ... See more keywords
Incremental Learning With Adaptive Model Search and a Nominal Loss Model
Sign Up to like & getrecommendations! Published in 2022 at "IEEE Access"
DOI: 10.1109/access.2022.3149598
Abstract: This paper addresses an incremental learning problem, in which tasks are learned sequentially without access to the previously trained dataset. Catastrophic forgetting is a significant bottleneck to incremental learning as the network performs poorly on… read more here.
Keywords: incremental learning; loss; model; model search ... See more keywords