Kazusato Oko
14 papers · 2022–2025 · 4 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+5 more ↓ Show less ↑
π Cross-Pollinator (11) π Conference Polyglot (4) πΊοΈ Taxonomy Completionist (25) π Interdisciplinary Bridge π§ Keyword Pioneer
π€
Dynamic Duo
(14)
π
Triple Crown
π
Keyword Champion
β‘
Prolific Year
(7)
π
Century Club
(14)
Conferences
ICLR (5)
ICML (5)
NIPS (3)
COLT (1)
Top co-authors
Keywords
neural network
(3)
representation learning
(2)
single-index model
(2)
sample complexity
(2)
feature learning
(1)
neural network training
(1)
transformer architecture
(1)
stochastic gradient descent
(1)
in-context learning
(1)
neural network optimization
(1)
nonlinear regression
(1)
gradient descent
(1)
gradient boosting
(1)
generalization error
(1)
minimax optimal
(1)
score matching
(1)
diffusion model
(1)
additive model
(1)
binary classification
(1)
statistical learning
(1)
Papers
Nonlinear transformers can perform inference-time feature learning
ICML 2025
Flow matching achieves almost minimax optimal convergence
ICLR 2025
Direct Distributional Optimization for Provable Alignment of Diffusion Models
ICLR 2025
Learning sum of diverse features: computational hardness and efficient gradient-based training for ridge combinations
COLT 2024
Mean Field Langevin Actor-Critic: Faster Convergence and Global Optimality beyond Lazy Learning
ICML 2024
SILVER: Single-loop variance reduction and application to federated learning
ICML 2024
Neural network learns low-dimensional polynomials with SGD near the information-theoretic limit
NIPS 2024
Pretrained Transformer Efficiently Learns Low-Dimensional Target Functions In-Context
NIPS 2024
Symmetric Mean-field Langevin Dynamics for Distributional Minimax Problems
ICLR 2024
Improved statistical and computational complexity of the mean-field Langevin dynamics under structured data
ICLR 2024
Feature learning via mean-field Langevin dynamics: classifying sparse parities and beyond
NIPS 2023
Primal and Dual Analysis of Entropic Fictitious Play for Finite-sum Problems
ICML 2023
Diffusion Models are Minimax Optimal Distribution Estimators
ICML 2023
Particle Stochastic Dual Coordinate Ascent: Exponential convergent algorithm for mean field neural network optimization
ICLR 2022