Masahito Ueda

Publication Activity (10 Years)

Years Active: 2003-2024
Publications (10 Years): 29

Top Topics

Portfolio Theory

Supervised Learning

Top Venues

Publications

Lennart Dabelow, Masahito Ueda
Symbolic Equation Solving via Reinforcement Learning. CoRR (2024)
Ziyin Liu, Hongchao Li, Masahito Ueda
Law of Balance and Stationary Distribution of Stochastic Gradient Descent. CoRR (2023)
Ziyin Liu, Botao Li, Tomer Galanti, Masahito Ueda
The Probabilistic Stability of Stochastic Gradient Descent. CoRR (2023)
Ziyin Liu, Ekdeep Singh Lubana, Masahito Ueda, Hidenori Tanaka
What shapes the loss landscape of self supervised learning? ICLR (2023)
Zhikang T. Wang, Masahito Ueda
Convergent and Efficient Deep Q Learning Algorithm. ICLR (2022)
Ziyin Liu, Kangqiao Liu, Takashi Mori, Masahito Ueda
Strength of Minibatch Noise in SGD. ICLR (2022)
Ziyin Liu, Botao Li, James B Simon, Masahito Ueda
SGD Can Converge to Local Maxima. ICLR (2022)
Takashi Mori, Masahito Ueda
Interplay between depth of neural networks and locality of target functions. CoRR (2022)
Ziyin Liu, Ekdeep Singh Lubana, Masahito Ueda, Hidenori Tanaka
What shapes the loss landscape of self-supervised learning? CoRR (2022)
Lennart Dabelow, Masahito Ueda
Three Learning Stages and Accuracy-Efficiency Tradeoff of Restricted Boltzmann Machines. CoRR (2022)
Ziyin Liu, Masahito Ueda
Exact Phase Transitions in Deep Learning. CoRR (2022)
Takashi Mori, Ziyin Liu, Kangqiao Liu, Masahito Ueda
Power-Law Escape Rate of SGD. ICML (2022)
Ziyin Liu, Hanlin Zhang, Xiangming Meng, Yuting Lu, Eric P. Xing, Masahito Ueda
Stochastic Neural Networks with Infinite Width are Deterministic. CoRR (2022)
Kangqiao Liu, Ziyin Liu, Masahito Ueda
Noise and Fluctuation of Finite Learning Rate Stochastic Gradient Descent. ICML (2021)
Ziyin Liu, Botao Li, Masahito Ueda
SGD May Never Escape Saddle Points. CoRR (2021)
Ziyin Liu, Kangqiao Liu, Takashi Mori, Masahito Ueda
On Minibatch Noise: Discrete-Time SGD, Overparametrization, and Bayes. CoRR (2021)
Zhikang T. Wang, Masahito Ueda
A Convergent and Efficient Deep Q Network Algorithm. CoRR (2021)
Takashi Mori, Ziyin Liu, Kangqiao Liu, Masahito Ueda
Logarithmic landscape and power-law escape rate of SGD. CoRR (2021)
Kangqiao Liu, Ziyin Liu, Masahito Ueda
Stochastic Gradient Descent with Large Learning Rate. CoRR (2020)
Ziyin Liu, Blair Chen, Ru Wang, Paul Pu Liang, Ruslan Salakhutdinov, Louis-Philippe Morency, Masahito Ueda
Learning Not to Learn in the Presence of Noisy Labels. CoRR (2020)
Ziyin Liu, Zhikang Wang, Masahito Ueda
LaProp: a Better Way to Combine Momentum with Adaptive Gradient. CoRR (2020)
Takashi Mori, Masahito Ueda
Is deeper better? It depends on locality of relevant features. CoRR (2020)
Ziyin Liu, Tilman Hartwig, Masahito Ueda
Neural Networks Fail to Learn Periodic Functions and How to Fix It. NeurIPS (2020)
Ziyin Liu, Tilman Hartwig, Masahito Ueda
Neural Networks Fail to Learn Periodic Functions and How to Fix It. CoRR (2020)
Takashi Mori, Masahito Ueda
Improved generalization by noise enhancement. CoRR (2020)
Ziyin Liu, Zihao Wang, Makoto Yamada, Masahito Ueda
Volumization as a Natural Generalization of Weight Decay. CoRR (2020)
Ziyin Liu, Zhikang Wang, Paul Pu Liang, Ruslan Salakhutdinov, Louis-Philippe Morency, Masahito Ueda
Deep Gamblers: Learning to Abstain with Portfolio Theory. CoRR (2019)
Ziyin Liu, Zhikang Wang, Paul Pu Liang, Ruslan Salakhutdinov, Louis-Philippe Morency, Masahito Ueda
Deep Gamblers: Learning to Abstain with Portfolio Theory. NeurIPS (2019)
Zhikang Wang, Yuto Ashida, Masahito Ueda
Deep Reinforcement Learning Control of Quantum Cartpoles. CoRR (2019)
Hiroaki Terashima, Masahito Ueda
Einstein-Podolsky-Rosen correlation seen from moving observers. Quantum Inf. Comput. 3 (3) (2003)