no code implementations • 15 Mar 2024 • Guoxi Zhang, Han Bao, Hisashi Kashima
To address this problem, the present study introduces a framework that consolidates offline preferences and \emph{virtual preferences} for PbRL, which are comparisons between the agent's behaviors and the offline data.
no code implementations • 20 Feb 2024 • Weiye Chen, Yiqun Xie, Xiaowei Jia, Erhu He, Han Bao, Bang An, Xun Zhou
When dealing with data from distinct locations, machine learning algorithms tend to demonstrate an implicit preference of some locations over the others, which constitutes biases that sabotage the spatial fairness of the algorithm.
no code implementations • 13 Feb 2024 • Shinsaku Sakaue, Han Bao, Taira Tsuchiya, Taihei Oki
We extend the exploit-the-surrogate-gap framework to online structured prediction with \emph{Fenchel--Young losses}, a large family of surrogate losses including the logistic loss for multiclass classification, obtaining finite surrogate regret bounds in various structured prediction problems.
no code implementations • 3 Feb 2024 • Han Bao, Ryuichiro Hataya, Ryo Karakida
To this end, we characterize the notion of attention localization by the eigenspectrum of query-key parameter matrices and reveal that a small eigenspectrum variance leads attention to be localized.
1 code implementation • 13 Oct 2023 • Ryoma Sato, Yuki Takezawa, Han Bao, Kenta Niwa, Makoto Yamada
LLMs can generate texts that cannot be distinguished from human-written texts.
no code implementations • 2 Oct 2023 • Yuki Takezawa, Ryoma Sato, Han Bao, Kenta Niwa, Makoto Yamada
Although existing watermarking methods have successfully detected texts generated by LLMs, they significantly degrade the quality of the generated texts.
no code implementations • 28 Sep 2023 • Han Bao
While learned representations may collapse into a single point due to the lack of the repulsive force at first sight, Tian et al. (2021) revealed through the learning dynamics analysis that the representations can avoid collapse if data augmentation is sufficiently stronger than regularization.
1 code implementation • 25 Sep 2023 • Xiaofeng Lin, Guoxi Zhang, Xiaotian Lu, Han Bao, Koh Takeuchi, Hisashi Kashima
One popular application of this estimation lies in the prediction of the impact of a treatment (e. g., a promotion) on an outcome (e. g., sales) of a particular unit (e. g., an item), known as the individual treatment effect (ITE).
no code implementations • 8 Aug 2023 • Edward Chen, Han Bao, Nam Dinh
The method, referred to as the Laplacian distributed decay for reliability (LADDR), determines the difference between the operational and training datasets, which is used to calculate a prediction's relative reliability.
1 code implementation • 7 Jun 2023 • Yuki Arase, Han Bao, Sho Yokoi
Monolingual word alignment is crucial to model semantic interactions between sentences.
no code implementations • 9 Apr 2023 • Yinhao Li, Jinrong Yang, Jianjian Sun, Han Bao, Zheng Ge, Li Xiao
Bounded by the inherent ambiguity of depth perception, contemporary multi-view 3D object detection methods fall into the performance bottleneck.
no code implementations • 20 Jan 2023 • Han Bao, Xun Zhou, Yiqun Xie, Yanhua Li, Xiaowei Jia
While deep learning approaches outperform conventional estimation techniques on tasks with abundant training data, the continuously evolving pandemic poses a significant challenge to solving this problem due to data nonstationarity, limited observations, and complex social contexts.
no code implementations • 26 Dec 2022 • Shintaro Nakamura, Han Bao, Masashi Sugiyama
Optimal transport (OT) has become a widely used tool in the machine learning field to measure the discrepancy between probability distributions.
1 code implementation • ICCV 2023 • Ryuichiro Hataya, Han Bao, Hiromi Arai
These trends lead us to a research question: "\textbf{will such generated images impact the quality of future datasets and the performance of computer vision models positively or negatively?}"
no code implementations • 30 Sep 2022 • Yuki Takezawa, Han Bao, Kenta Niwa, Ryoma Sato, Makoto Yamada
In this study, we propose Momentum Tracking, which is a method with momentum whose convergence rate is proven to be independent of data heterogeneity.
3 code implementations • 21 Sep 2022 • Yinhao Li, Han Bao, Zheng Ge, Jinrong Yang, Jianjian Sun, Zeming Li
To this end, we introduce an effective temporal stereo method to dynamically select the scale of matching candidates, enable to significantly reduce computation overhead.
Ranked #11 on 3D Object Detection on nuScenes Camera Only
no code implementations • 24 Jun 2022 • Makoto Yamada, Yuki Takezawa, Ryoma Sato, Han Bao, Zornitsa Kozareva, Sujith Ravi
In this paper, we aim to approximate the 1-Wasserstein distance by the tree-Wasserstein distance (TWD), where TWD is a 1-Wasserstein distance with tree-based embedding and can be computed in linear time with respect to the number of nodes on a tree.
no code implementations • 7 Apr 2022 • Han Bao, Hongbin Zhang, Tate Shorthill, Edward Chen, Svetlana Lawrence
This paper proposes a Platform for Risk Assessment of DIC (PRADIC) that is developed by Idaho National Laboratory (INL).
no code implementations • 17 Dec 2021 • Hongbin Zhang, Han Bao, Tate Shorthill, Edward Quinn
Existing analyses of CCFs in I&C systems mainly focus on hardware failures.
1 code implementation • 6 Oct 2021 • Han Bao, Yoshihiro Nagano, Kento Nozawa
Recent theoretical studies have attempted to explain the benefit of the large negative sample size by upper-bounding the downstream classification loss with the contrastive loss.
no code implementations • 26 Sep 2020 • Han Bao, Shenchao Jin, Junlei Duan, Suotang Jia, Klaus Mølmer, Heng Shen, Yanhong Xiao
In quantum mechanics, the Heisenberg uncertainty relation presents an ultimate limit to the precision by which one can predict the outcome of position and momentum measurements on a particle.
Quantum Physics
no code implementations • 11 Jun 2020 • Han Bao, Takuya Shimada, Liyuan Xu, Issei Sato, Masashi Sugiyama
A classifier built upon the representations is expected to perform well in downstream classification; however, little theory has been given in literature so far and thereby the relationship between similarity and classification has remained elusive.
no code implementations • 28 May 2020 • Han Bao, Clayton Scott, Masashi Sugiyama
Adversarially robust classification seeks a classifier that is insensitive to adversarial perturbations of test patterns.
no code implementations • 7 May 2020 • Han Bao, Jinyong Feng, Nam Dinh, Hongbin Zhang
Development of those closures traditionally rely on the experimental data and analytical derivation with simplified assumptions that usually cannot deliver a universal solution across a wide range of flow conditions.
no code implementations • 3 Feb 2020 • Soham Dan, Han Bao, Masashi Sugiyama
We perform a detailed investigation of this problem under two realistic noise models and propose two algorithms to learn from noisy S-D data.
no code implementations • 6 Jan 2020 • Han Bao, Nam Dinh, Linyu Lin, Robert Youngblood, Jeffrey Lane, Hongbin Zhang
Current system thermal-hydraulic codes have limited credibility in simulating real plant conditions, especially when the geometry and boundary conditions are extrapolated beyond the range of test facilities.
no code implementations • 7 Nov 2019 • Han Bao
Segmentation of objects with various sizes is relatively less explored in medical imaging, and has been very challenging in computer vision tasks in general.
no code implementations • 17 Oct 2019 • Han Bao, Jinyong Feng, Nam Dinh, Hongbin Zhang
To realize efficient computational fluid dynamics (CFD) prediction of two-phase flow, a multi-scale framework was proposed in this paper by applying a physics-guided data-driven approach.
no code implementations • 3 Jul 2019 • Yanyuet Man, Xiangyun Ding, Xingcheng Yao, Han Bao
The proposed EM approach is based on the collaborative filtering among the annotated and unannotated datasets.
no code implementations • 29 May 2019 • Han Bao, Masashi Sugiyama
A clue to tackle their direct optimization is a calibrated surrogate utility, which is a tractable lower bound of the true utility function representing a given metric.
no code implementations • 26 Apr 2019 • Takuya Shimada, Han Bao, Issei Sato, Masashi Sugiyama
In this paper, we derive an unbiased risk estimator which can handle all of similarities/dissimilarities and unlabeled data.
no code implementations • 27 Jan 2019 • Yueh-Hua Wu, Nontawat Charoenphakdee, Han Bao, Voot Tangkaratt, Masashi Sugiyama
Imitation learning (IL) aims to learn an optimal policy from demonstrations.
no code implementations • 11 Sep 2018 • Seiichi Kuroki, Nontawat Charoenphakdee, Han Bao, Junya Honda, Issei Sato, Masashi Sugiyama
A previously proposed discrepancy that does not use the source domain labels requires high computational cost to estimate and may lead to a loose generalization error bound in the target domain.
2 code implementations • ICML 2018 • Han Bao, Gang Niu, Masashi Sugiyama
Supervised learning needs a huge amount of labeled data, which can be a big bottleneck under the situation where there is a privacy concern or labeling cost is high.
1 code implementation • 22 Apr 2017 • Han Bao, Tomoya Sakai, Issei Sato, Masashi Sugiyama
Multiple instance learning (MIL) is a variation of traditional supervised learning problems where data (referred to as bags) are composed of sub-elements (referred to as instances) and only bag labels are available.