You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Luo, Haipeng, and Robert E. Schapire. 2014. “A Drifting-Games Analysis for Online Learning and Applications to Boosting.” In Advances in Neural Information Processing Systems, edited by Z. Ghahramani, M. Welling, C. Cortes, N. Lawrence, and K. Q. Weinberger, 27:1368–76. Curran Associates, Inc.
The text was updated successfully, but these errors were encountered:
一言でいうと
Parameter-freeな適応的最適化手法であるAdaNormalHedgeを提案.
論文リンク
著者/所属機関
Haipeng Luo (Princeton University), Robert E. Schapire (Microsoft Research)
投稿日付(yyyy/MM/dd)
2015/02/20
概要
エキスパート付き予測問題のオンライン学習において,複数の目的関数を事前知識なしに同時に最適化するparameter-freeな適応的アルゴリズムを提案.
提案手法であるAdaNormalHedgeはNormalHedge.DT algorithm (Luo and Schapire, 2014)の改良版になっている.
提案手法は,
ことを保証している.
新規性・差分
NormalHedge.DTからの改善として
手法
結果
コメント
The text was updated successfully, but these errors were encountered: