no code implementations • 2 Apr 2024 • Kyungbok Lee, Myunghee Cho Paik
We introduce a novel doubly-robust (DR) off-policy evaluation (OPE) estimator for Markov decision processes, DRUnknown, designed for situations where both the logging policy and the value function are unknown.
1 code implementation • 20 Aug 2023 • Young-geun Kim, Kyungbok Lee, Youngwon Choi, Joong-Ho Won, Myunghee Cho Paik
The conditional distributions given unobserved intermediate domains are on the Wasserstein geodesic between conditional distributions given two observed domain labels.
no code implementations • 13 Mar 2023 • Gi-Soo Kim, Young Suh Hong, Tae Hoon Lee, Myunghee Cho Paik, Hongsoo Kim
Long-term care service for old people is in great demand in most of the aging societies.
no code implementations • 15 Sep 2022 • Wonyoung Kim, Kyungbok Lee, Myunghee Cho Paik
We propose a novel contextual bandit algorithm for generalized linear rewards with an $\tilde{O}(\sqrt{\kappa^{-1} \phi T})$ regret over $T$ rounds where $\phi$ is the minimum eigenvalue of the covariance of contexts and $\kappa$ is a lower bound of the variance of rewards.
no code implementations • 11 Jun 2022 • Wonyoung Kim, Myunghee Cho Paik, Min-hwan Oh
We propose a linear contextual bandit algorithm with $O(\sqrt{dT\log T})$ regret bound, where $d$ is the dimension of contexts and $T$ isthe time horizon.
no code implementations • 17 May 2022 • Young-Geun Choi, Gi-Soo Kim, Seunghoon Paik, Myunghee Cho Paik
Non-stationarity is ubiquitous in human behavior and addressing it in the contextual bandits is challenging.
no code implementations • NeurIPS 2021 • Wonyoung Kim, Gi-Soo Kim, Myunghee Cho Paik
A challenging aspect of the bandit problem is that a stochastic reward is observed only for the chosen arm and the rewards of other arms remain missing.
no code implementations • 1 Feb 2021 • Wonyoung Kim, Gi-Soo Kim, Myunghee Cho Paik
A challenging aspect of the bandit problem is that a stochastic reward is observed only for the chosen arm and the rewards of other arms remain missing.
1 code implementation • 4 Dec 2020 • Minjin Kim, Young-geun Kim, Dongha Kim, Yongdai Kim, Myunghee Cho Paik
The Mixup method (Zhang et al. 2018), which uses linearly interpolated data, has emerged as an effective data augmentation tool to improve generalization performance and the robustness to adversarial examples.
1 code implementation • ICML 2020 • Yongchan Kwon, Wonyoung Kim, Joong-Ho Won, Myunghee Cho Paik
We show that our approximation and risk consistency results naturally extend to the cases when data are locally perturbed.
1 code implementation • NeurIPS 2019 • Gi-Soo Kim, Myunghee Cho Paik
Contextual multi-armed bandit algorithms are widely used in sequential decision tasks such as news article recommendation systems, web page ad placement algorithms, and mobile health.
no code implementations • 31 Jan 2019 • Gi-Soo Kim, Myunghee Cho Paik
We prove that the high-probability upper bound of the regret incurred by the proposed algorithm has the same order as the Thompson sampling algorithm for linear reward models.
1 code implementation • 28 Jan 2019 • Yongchan Kwon, Wonyoung Kim, Masashi Sugiyama, Myunghee Cho Paik
We consider the problem of learning a binary classifier from only positive and unlabeled observations (called PU learning).
no code implementations • MIDL 2018 Conference 2018 • Yongchan Kwon, Joong-Ho Won, Beom Joon Kim, Myunghee Cho Paik
Most recent research of neural networks in the field of computer vision has focused on improving accuracy of point predictions by developing various network architectures or learning algorithms.
General Classification Ischemic Stroke Lesion Segmentation +2