Kazushi Ikeda
4 papers · 2019–2024 · 4 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 ↓
π
Conference Polyglot Β· Bronze
π
Academic Marathon Β· Sprint
π
Interdisciplinary Bridge Β· Bronze
πΊοΈ
Taxonomy Completionist
(18)
π
Trend Setter
Venues
Top co-authors
Research topics
Machine Learning
(3)
Artificial Intelligence
(2)
Core AI
(2)
Learning Paradigms
(2)
Optimization & Theory
(2)
Deep Learning
(1)
Mathematics & Optimization
(1)
Natural Language Processing
(1)
Reinforcement Learning
(1)
Application Areas
(1)
Architectures
(1)
Generation
(1)
Learning Types
(1)
Methods
(1)
Optimization
(1)
Keywords
zero-shot learning
(1)
fact verification
(1)
batch normalization
(1)
information retrieval
(1)
neural network optimization
(1)
feature representation
(1)
empirical risk minimization
(1)
markov decision process
(1)
hidden layer
(1)
state transition
(1)
deep neural network
(1)
latent factor
(1)
skip connection
(1)
dialogue system
(1)
gradient magnitude
(1)
heavy-tailed data
(1)
large language model
(1)
robust gradient descent
(1)
strategy extraction
(1)
data separability
(1)
Papers
Identifying Latent State-Transition Processes for Individualized Reinforcement Learning
NeurIPS 2024
Zero-shot Persuasive Chatbots with LLM-Generated Strategies and Information Retrieval
EMNLP 2024
Better generalization with less data using robust gradient descent
ICML 2019
ResNet and Batch-normalization Improve Data Separability
ACML 2019