Atsutoshi Kumagai
23 papers · 2017–2025 · 6 venues · across top CS/AI venues
Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.
Achievements
Jump to papers ↓+8 more ↓ Show less ↑
πΊοΈ Taxonomy Completionist (38) π Conference Polyglot Β· Silver π Academic Marathon Β· Sprint π Interdisciplinary Bridge Β· Bronze π£ Hot Topic Early Bird
π
Grand Slam
π€
Dynamic Duo
(16)
β‘
Prolific Year Β· Productive
π₯
Unstoppable Β· Bronze
π
Century Club Β· Bronze
π
Conference Pioneer
π
Trend Setter
ποΈ
Keyword Collector
(84)
Top co-authors
Research topics
Machine Learning
(19)
Learning Types Β· Machine Learning
(11)
Deep Learning
(9)
Core Methods
(9)
Application Areas
(8)
Artificial Intelligence
(7)
Learning Paradigms Β· Artificial Intelligence
(7)
Learning Types Β· Deep Learning
(7)
Optimization & Theory
(5)
Mathematics & Optimization
(4)
Learning Paradigms Β· Machine Learning
(4)
Optimization
(4)
Architectures
(2)
Models
(2)
Computer Vision
(1)
Keywords
few-shot learning
(8)
transfer learning
(4)
positive-unlabeled learning
(3)
feature selection
(3)
neural network
(3)
unsupervised domain adaptation
(2)
straight-through estimator
(2)
domain adaptation
(2)
latent representation
(2)
anomaly detection
(2)
distribution shift
(2)
importance weighting
(2)
sparse optimization
(2)
linear mode connectivity
(2)
covariate shift
(2)
density ratio estimation
(2)
optimal transport
(1)
gradient-based optimization
(1)
non-convex optimization
(1)
compressive sensing
(1)
Papers
Analysis of Linear Mode Connectivity via Permutation-Based Weight Matching: With Insights into Other Permutation Search Methods
ICLR 2025
Importance-weighted Positive-unlabeled Learning for Distribution Shift Adaptation
AISTATS 2025
Linear Mode Connectivity between Multiple Models modulo Permutation Symmetries
ICML 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
Positive-unlabeled AUC Maximization under Covariate Shift
ICML 2025
Positive-Unlabeled Diffusion Models for Preventing Sensitive Data Generation
ICLR 2025
Test-time Adaptation for Regression by Subspace Alignment
ICLR 2025
AUC Maximization under Positive Distribution Shift
NeurIPS 2024
Fast Iterative Hard Thresholding Methods with Pruning Gradient Computations
NeurIPS 2024
Zero-Shot Task Adaptation with Relevant Feature Information
AAAI 2024
Fast Block Coordinate Descent for Non-Convex Group Regularizations
AISTATS 2023
Fast Regularized Discrete Optimal Transport with Group-Sparse Regularizers
AAAI 2023
Meta-learning for Robust Anomaly Detection
AISTATS 2023
Regularizing Neural Networks with Meta-Learning Generative Models
NeurIPS 2023
Few-shot Learning for Feature Selection with Hilbert-Schmidt Independence Criterion
NeurIPS 2022
Meta-ticket: Finding optimal subnetworks for few-shot learning within randomly initialized neural networks
NeurIPS 2022
Sharing Knowledge for Meta-learning with Feature Descriptions
NeurIPS 2022
Meta-Learning for Relative Density-Ratio Estimation
NeurIPS 2021
Meta-learning from Tasks with Heterogeneous Attribute Spaces
NeurIPS 2020
Transfer Anomaly Detection by Inferring Latent Domain Representations
NeurIPS 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