← Authors

Atsutoshi Kumagai

23 papers · 2017–2025 · 6 conferences · across top CS/AI conferences

Achievements

🌈 Renaissance Researcher (5) 🐝 Cross-Pollinator (13) 🧭 Keyword Pioneer πŸŒ‰ Interdisciplinary Bridge πŸ—ΊοΈ Taxonomy Completionist (35) 🐣 Hot Topic Early Bird 🌍 Conference Polyglot (6) πŸƒ Academic Marathon (8) 🀝 Dynamic Duo (16) πŸ† Grand Slam πŸ”₯ Unstoppable (7) πŸ“ˆ Trend Setter πŸ’Ž Century Club (23) πŸš€ Conference Pioneer πŸ—ƒοΈ Keyword Collector (55) ⚑ Prolific Year (8)

Conferences

NIPS (9) AISTATS (5) AAAI (3) ICLR (3) ICML (2) IJCAI (1)

Top co-authors

Tomoharu Iwata (16) Yasuhiro Fujiwara (10) Yasutoshi Ida (6) Hiroshi Takahashi (5) Sekitoshi Kanai (4) Shin'ya Yamaguchi (3) Taishi Nishiyama (3) Kazuki Adachi (3) Akira Ito (2) Daiki Chijiwa (2)

Keywords

few-shot learning (6) transfer learning (4) feature selection (3) neural network (3) unsupervised domain adaptation (2) distribution shift (2) anomaly detection (2) sparse optimization (2) latent representation (2) data augmentation (1) optimal transport (1) gradient-based optimization (1) binary classification (1) feature learning (1) compressive sensing (1) non-convex optimization (1) distribution matching (1) outlier detection (1) sparse regression (1) positive unlabeled learning (1)

Papers

Linear Mode Connectivity between Multiple Models modulo Permutation Symmetries ICML 2025
Positive-unlabeled AUC Maximization under Covariate Shift ICML 2025
Importance-weighted Positive-unlabeled Learning for Distribution Shift Adaptation AISTATS 2025
Meta-learning from Heterogeneous Tensors for Few-shot Tensor Completion AISTATS 2025
Meta-learning Task-specific Regularization Weights for Few-shot Linear Regression AISTATS 2025
Test-time Adaptation for Regression by Subspace Alignment ICLR 2025
Positive-Unlabeled Diffusion Models for Preventing Sensitive Data Generation ICLR 2025
Analysis of Linear Mode Connectivity via Permutation-Based Weight Matching: With Insights into Other Permutation Search Methods ICLR 2025
Fast Iterative Hard Thresholding Methods with Pruning Gradient Computations NIPS 2024
Zero-Shot Task Adaptation with Relevant Feature Information AAAI 2024
AUC Maximization under Positive Distribution Shift NIPS 2024
Regularizing Neural Networks with Meta-Learning Generative Models NIPS 2023
Meta-learning for Robust Anomaly Detection AISTATS 2023
Fast Block Coordinate Descent for Non-Convex Group Regularizations AISTATS 2023
Fast Regularized Discrete Optimal Transport with Group-Sparse Regularizers AAAI 2023
Few-shot Learning for Feature Selection with Hilbert-Schmidt Independence Criterion NIPS 2022
Sharing Knowledge for Meta-learning with Feature Descriptions NIPS 2022
Meta-ticket: Finding optimal subnetworks for few-shot learning within randomly initialized neural networks NIPS 2022
Meta-Learning for Relative Density-Ratio Estimation NIPS 2021
Meta-learning from Tasks with Heterogeneous Attribute Spaces NIPS 2020
Transfer Anomaly Detection by Inferring Latent Domain Representations NIPS 2019
Unsupervised Domain Adaptation by Matching Distributions Based on the Maximum Mean Discrepancy via Unilateral Transformations AAAI 2019
Learning Latest Classifiers without Additional Labeled Data IJCAI 2017