Yuhei Umeda
10 papers · 2020–2025 · 7 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 ↓+3 more ↓ Show less ↑
🐣 Hot Topic Early Bird 🌍 Conference Polyglot · Silver 🏃 Academic Marathon · Sprint 🌉 Interdisciplinary Bridge · Bronze 🗺️ Taxonomy Completionist (26)
💎
Century Club · Bronze
🔥
Unstoppable · Bronze
🗃️
Keyword Collector
(52)
Top co-authors
Research topics
Machine Learning
(10)
Learning Types
(5)
Mathematics & Optimization
(4)
Core Methods
(4)
Optimization & Theory
(4)
Optimization
(3)
Artificial Intelligence
(2)
Deep Learning
(2)
Mathematics
(2)
Computer Vision
(1)
Interdisciplinary
(1)
Analysis
(1)
Application Areas
(1)
Core AI
(1)
Learning Paradigms
(1)
Keywords
topological data analysis
(3)
persistence diagram
(2)
contrastive learning
(1)
graph classification
(1)
uncertainty quantification
(1)
self-supervised learning
(1)
scene graph generation
(1)
multi-armed bandit
(1)
deep neural network
(1)
reproducing kernel hilbert space
(1)
gradient descent
(1)
arm selection
(1)
best arm identification
(1)
persistent homology
(1)
cost-sensitive learning
(1)
quantum computing
(1)
upper confidence bound
(1)
regret bound
(1)
semi-supervised learning
(1)
stochastic optimization
(1)
Papers
Instance-Optimal Pure Exploration for Linear Bandits on Continuous Arms
ICML 2025
Model-Based Best Arm Identification for Decreasing Bandits
AISTATS 2024
Quantum Kernelized Bandits
UAI 2024
Selective Mixup Fine-Tuning for Optimizing Non-Decomposable Objectives
ICLR 2024
Improving Predicate Representation in Scene Graph Generation by Self-Supervised Learning
WACV 2023
Cost-Sensitive Self-Training for Optimizing Non-Decomposable Metrics
NeurIPS 2022
ATOL: Measure Vectorization for Automatic Topologically-Oriented Learning
AISTATS 2021
Optimizing persistent homology based functions
ICML 2021
Topological Uncertainty: Monitoring Trained Neural Networks through Persistence of Activation Graphs
IJCAI 2021
PersLay: A Neural Network Layer for Persistence Diagrams and New Graph Topological Signatures
AISTATS 2020