45 citations · 367 across the 61 of their papers we have counts for
65 papers
Controlling the Diversity-Quality Trade-Off of LLMs by Merging Models Before and After Alignment
Yasuaki Sumita, Tomoharu Iwata, Toshiyuki Tanaka
Alignment is known to change the output characteristics of large language models (LLMs). Base models tend to generate more diverse outputs, whereas aligned models tend to produce h…
Partial AUC Maximization from Positive-unlabeled Data
Atsutoshi Kumagai, Tomoharu Iwata, Taishi Nishiyama +3
The partial area under the receiver operating characteristic curve (pAUC) is an important performance metric for binary classification that summarizes true positive rates within a…
Importance Weighting for Unlabeled-unlabeled Learning under Distribution Shift
Atsutoshi Kumagai, Tomoharu Iwata, Hiroshi Takahashi +3
Unlabeled-unlabeled (UU) learning allows us to learn a binary classifier from two sets of unlabeled data with different class-priors. It is a general framework because it includes…
AUC Maximization from Biased Positive-unlabeled Data with Confidence
Atsutoshi Kumagai, Tomoharu Iwata, Hiroshi Takahashi +3
Maximizing the area under the receiver operating characteristic curve (AUC) is a standard approach to imbalanced binary classification. Although positive and negative data are requ…
Meta-learning Representations for Learning from Multiple Annotators
Atsutoshi Kumagai, Tomoharu Iwata, Taishi Nishiyama +2
We propose a meta-learning method for learning from multiple noisy annotators. In many applications such as crowdsourcing services, labels for supervised learning are given by mult…
Positive-Unlabeled Diffusion Models for Preventing Sensitive Data Generation
Hiroshi Takahashi, Tomoharu Iwata, Atsutoshi Kumagai +2
Diffusion models are powerful generative models but often generate sensitive data that are unwanted by users, mainly because the unlabeled training data frequently contain such sen…
Meta-learning for Positive-unlabeled Classification
Atsutoshi Kumagai, Tomoharu Iwata, Yasuhiro Fujiwara
We propose a meta-learning method for positive and unlabeled (PU) classification, which improves the performance of binary classifiers obtained from only PU data in unseen target t…
Deep Positive-Unlabeled Anomaly Detection for Contaminated Unlabeled Data
Hiroshi Takahashi, Tomoharu Iwata, Atsutoshi Kumagai +1
Semi-supervised anomaly detection, which aims to improve the anomaly detection performance by using a small amount of labeled anomaly data in addition to unlabeled data, has attrac…
Neural Operators Meet Energy-based Theory: Operator Learning for Hamiltonian and Dissipative PDEs
Yusuke Tanaka, Takaharu Yaguchi, Tomoharu Iwata +1
The operator learning has received significant attention in recent years, with the aim of learning a mapping between function spaces. Prior works have proposed deep neural networks…
Meta-Learning for Neural Network-based Temporal Point Processes
Yoshiaki Takimoto, Yusuke Tanaka, Tomoharu Iwata +4
Human activities generate various event sequences such as taxi trip records, bike-sharing pick-ups, crime occurrence, and infectious disease transmission. The point process is wide…
Meta-learning to Calibrate Gaussian Processes with Deep Kernels for Regression Uncertainty Estimation
Tomoharu Iwata, Atsutoshi Kumagai
Although Gaussian processes (GPs) with deep kernels have been successfully used for meta-learning in regression tasks, its uncertainty estimation performance can be poor. We propos…
Meta-learning of semi-supervised learning from tasks with heterogeneous attribute spaces
Tomoharu Iwata, Atsutoshi Kumagai
We propose a meta-learning method for semi-supervised learning that learns from multiple tasks with heterogeneous attribute spaces. The existing semi-supervised meta-learning metho…
Meta-learning of Physics-informed Neural Networks for Efficiently Solving Newly Given PDEs
Tomoharu Iwata, Yusuke Tanaka, Naonori Ueda
We propose a neural network-based meta-learning method to efficiently solve partial differential equation (PDE) problems. The proposed method is designed to meta-learn how to solve…
Information-theoretic Analysis of Test Data Sensitivity in Uncertainty
Futoshi Futami, Tomoharu Iwata
Bayesian inference is often utilized for uncertainty quantification tasks. A recent analysis by Xu and Raginsky 2022 rigorously decomposed the predictive uncertainty in Bayesian in…
Meta-learning for heterogeneous treatment effect estimation with closed-form solvers
Tomoharu Iwata, Yoichi Chikahara
This article proposes a meta-learning method for estimating the conditional average treatment effect (CATE) from a few observational data. The proposed method learns how to estimat…
Modeling Nonlinear Dynamics in Continuous Time with Inductive Biases on Decay Rates and/or Frequencies
Tomoharu Iwata, Yoshinobu Kawahara
We propose a neural network-based model for nonlinear dynamics in continuous time that can impose inductive biases on decay rates and/or frequencies. Inductive biases are helpful f…
Linear Embedding-based High-dimensional Batch Bayesian Optimization without Reconstruction Mappings
Shuhei A. Horiguchi, Tomoharu Iwata, Taku Tsuzuki +1
The optimization of high-dimensional black-box functions is a challenging problem. When a low-dimensional linear embedding structure can be assumed, existing Bayesian optimization…
Active Learning for Regression with Aggregated Outputs
Tomoharu Iwata
Due to the privacy protection or the difficulty of data collection, we cannot observe individual outputs for each instance, but we can observe aggregated outputs that are summed ov…
Data-driven End-to-end Learning of Pole Placement Control for Nonlinear Dynamics via Koopman Invariant Subspaces
Tomoharu Iwata, Yoshinobu Kawahara
We propose a data-driven method for controlling the frequency and convergence rate of black-box nonlinear dynamical systems based on the Koopman operator theory. With the proposed…
Predicting Opinion Dynamics via Sociologically-Informed Neural Networks
Maya Okawa, Tomoharu Iwata
Opinion formation and propagation are crucial phenomena in social networks and have been extensively studied across several disciplines. Traditionally, theoretical models of opinio…
Aggregated Multi-output Gaussian Processes with Knowledge Transfer Across Domains
Yusuke Tanaka, Toshiyuki Tanaka, Tomoharu Iwata +4
Aggregate data often appear in various fields such as socio-economics and public security. The aggregate data are associated not with points but with supports (e.g., spatial region…
Meta-learning for Out-of-Distribution Detection via Density Estimation in Latent Space
Tomoharu Iwata, Atsutoshi Kumagai
Many neural network-based out-of-distribution (OoD) detection methods have been proposed. However, they require many training data for each target task. We propose a simple yet eff…
Excess risk analysis for epistemic uncertainty with application to variational inference
Futoshi Futami, Tomoharu Iwata, Naonori Ueda +2
Bayesian deep learning plays an important role especially for its ability evaluating epistemic uncertainty (EU). Due to computational complexity issues, approximation methods such…
Tight integration of neural- and clustering-based diarization through deep unfolding of infinite Gaussian mixture model
Keisuke Kinoshita, Marc Delcroix, Tomoharu Iwata
Speaker diarization has been investigated extensively as an important central task for meeting analysis. Recent trend shows that integration of end-to-end neural (EEND)-and cluster…