no code implementations • 8 Mar 2023 • Masahiro Kato, Shuting Wu, Kodai Kureishi, Shota Yasui
Therefore, the positive labels that we observe are a combination of both the exposure and the labeling, which creates a selection bias problem for the observed positive samples.
no code implementations • NeurIPS 2021 • Masahiro Kato, Kenichiro McAlinn, Shota Yasui
This paper proposes a DR estimator for dependent samples obtained from adaptive experiments.
no code implementations • ICLR 2022 • Masahiro Kato, Masaaki Imaizumi, Kenichiro McAlinn, Shota Yasui, Haruo Kakehi
We consider learning causal relationships under conditional moment restrictions.
no code implementations • 3 Aug 2021 • Masahiro Kato, Masaaki Imaizumi, Kenichiro McAlinn, Haruo Kakehi, Shota Yasui
To address this issue, we propose a method that transforms conditional moment restrictions to unconditional moment restrictions through importance weighting, using a conditional density ratio estimator.
no code implementations • 23 Oct 2020 • Masahiro Kato, Kenshi Abe, Kaito Ariu, Shota Yasui
Based on the properties of the evaluation policy, we categorize OPE situations.
no code implementations • 8 Oct 2020 • Masahiro Kato, Shota Yasui, Kenichiro McAlinn
This paper proposes a DR estimator for dependent samples obtained from adaptive experiments.
no code implementations • 28 Sep 2020 • Masahiro Kato, Shota Yasui
We consider training a binary classifier under delayed feedback (\emph{DF learning}).
1 code implementation • NeurIPS 2020 • Masahiro Kato, Masatoshi Uehara, Shota Yasui
Then, we propose doubly robust and efficient estimators for OPE and OPL under a covariate shift by using a nonparametric estimator of the density ratio between the historical and evaluation data distributions.
no code implementations • 20 Feb 2020 • Yusuke Narita, Shota Yasui, Kohei Yata
Efficient methods to evaluate new algorithms are critical for improving interactive bandit and reinforcement learning systems such as recommendation systems.
1 code implementation • 6 Feb 2020 • Shota Yasui, Gota Morishita, Komei Fujita, Masashi Shibata
We prove its consistency for the feedback shift.
no code implementations • 4 Oct 2019 • Yuta Saito, Gota Morishita, Shota Yasui
To overcome these challenges, we propose two unbiased estimators: one for CVR prediction and the other for bias estimation.
1 code implementation • ICML 2020 • Yuta Saito, Shota Yasui
We study the model selection problem in conditional average treatment effect (CATE) prediction.
1 code implementation • 21 Aug 2019 • Daisuke Moriwaki, Komei Fujita, Shota Yasui, Takahiro Hoshino
In online display advertising, selecting the most effective ad creative (ad image) for each impression is a crucial task for DSPs (Demand-Side Platforms) to fulfill their goals (click-through rate, number of conversions, revenue, and brand improvement).
no code implementations • 10 Sep 2018 • Yusuke Narita, Shota Yasui, Kohei Yata
What is the most statistically efficient way to do off-policy evaluation and optimization with batch data from bandit feedback?
Ranked #1 on Visual Object Tracking on VOT2014