セミナー

理研AIPセミナー

タイトル On approximation ability for Besov space by deep ReLU network
開催日時 2019年10月30日 13:30 - 14:30 + 30 min
主催者
講演者 Koichi Taniguchi 氏 (Nagoya University)
場所 Keio University, Yagami-campus, Bldg.14th,
Room 631 A/B
内容 Recently, it has been shown that deep learning outperforms any linear estimator such as kernel ridge regression, where the target function has highly spatial inhomogeneity of its smoothness. To generalize these results, we consider the approximation and estimation error bounds of deep ReLU networks where the target function is in a Besov space with variable smoothness. The Besov space is a function space with three exponents (i.e., smoothness exponent, integrability exponent and interpolation exponent), which includes H\"older space and Sobolev space. This talk is based on the joint work with Sho Sonoda (RIKEN), Masahiro Ikeda (RIKEN/ Keio Univ.), Kenta Oono (Tokyo Univ./Preferred Networks), and Taiji Suzuki (Tokyo Univ./RIKEN).
資料
URL

PAGETOP