Masahito Ueda
8 papers · 2019–2023 · 3 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 · Bronze
🌉
Interdisciplinary Bridge · Bronze
🗺️
Taxonomy Completionist
(17)
🔥
Unstoppable · Bronze
❓
The Questioner
Venues
Top co-authors
Research topics
Machine Learning
(7)
Optimization & Theory · Machine Learning
(6)
Artificial Intelligence
(3)
Deep Learning
(3)
Core AI
(3)
Core Methods
(2)
Mathematics & Optimization
(1)
Reinforcement Learning
(1)
Application Areas
(1)
Learning Types · Deep Learning
(1)
Learning Types · Machine Learning
(1)
Methods
(1)
Optimization & Theory · Deep Learning
(1)
Probability
(1)
Techniques
(1)
Keywords
stochastic gradient descent
(4)
saddle point
(2)
learning rate
(2)
escape rate
(2)
neural network optimization
(1)
loss landscape
(1)
optimization landscape
(1)
optimization theory
(1)
selective classification
(1)
stationary distribution
(1)
convergence guarantee
(1)
inductive bia
(1)
hessian eigenvalue
(1)
implicit regularization
(1)
implicit bia
(1)
stochastic differential equation
(1)
activation function
(1)
dimensional collapse
(1)
mini-batch sampling
(1)
deep q-network
(1)
Papers
What shapes the loss landscape of self supervised learning?
ICLR 2023
Convergent and Efficient Deep Q Learning Algorithm
ICLR 2022
Power-Law Escape Rate of SGD
ICML 2022
SGD Can Converge to Local Maxima
ICLR 2022
Strength of Minibatch Noise in SGD
ICLR 2022
Noise and Fluctuation of Finite Learning Rate Stochastic Gradient Descent
ICML 2021
Neural Networks Fail to Learn Periodic Functions and How to Fix It
NeurIPS 2020
Deep Gamblers: Learning to Abstain with Portfolio Theory
NeurIPS 2019