Hideaki Iiduka
8 papers · 2023–2026 · 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 ↓
🌍
Conference Polyglot · Silver
🌉
Interdisciplinary Bridge · Bronze
🗺️
Taxonomy Completionist
(11)
🏆
Keyword Champion
(2)
Top co-authors
Research topics
Keywords
stochastic gradient descent
(4)
generative adversarial network
(3)
batch size
(3)
stochastic first-order oracle
(2)
non-convex optimization
(2)
convergence analysis
(2)
convergence rate
(2)
conjugate gradient method
(2)
deep neural network
(2)
stationary point
(2)
momentum optimization
(1)
adaptive method
(1)
local nash equilibrium
(1)
jensen-shannon divergence
(1)
frechet inception distance
(1)
heavy-tailed noise
(1)
graduated optimization
(1)
neural network
(1)
multimodal optimization
(1)
two time-scale update rule
(1)
Papers
Vanilla SGD with Momentum Survives Heavy-Tailed Noise: Convergence Analysis without Gradient Clipping or Normalization
UAI 2026
Both Asymptotic and Non-Asymptotic Convergence of Quasi-Hyperbolic Momentum using Increasing Batch Size
ACML 2025
Explicit and Implicit Graduated Optimization in Deep Neural Networks
AAAI 2025
Faster Convergence of Riemannian Stochastic Gradient Descent with Increasing Batch Size
ACML 2025
Increasing Batch Size Improves Convergence of Stochastic Gradient Descent with Momentum
ACML 2025
Scaled Conjugate Gradient Method for Nonconvex Optimization in Deep Neural Networks
JMLR 2024
Conjugate Gradient Method for Generative Adversarial Networks
AISTATS 2023
Existence and Estimation of Critical Batch Size for Training Generative Adversarial Networks with Two Time-Scale Update Rule
ICML 2023