Denny Wu

Publication Activity (10 Years)

Years Active: 2018-2024
Publications (10 Years): 36

Top Topics

High Dimensions

Stochastic Gradient

Top Venues

Publications

Kazusato Oko, Yujin Song, Taiji Suzuki, Denny Wu
Learning sum of diverse features: computational hardness and efficient gradient-based training for ridge combinations. COLT (2024)
Atsushi Nitanda, Kazusato Oko, Taiji Suzuki, Denny Wu
Improved statistical and computational complexity of the mean-field Langevin dynamics under structured data. ICLR (2024)
Zhichao Wang, Denny Wu, Zhou Fan
Nonlinear spiked covariance matrices and signal propagation in deep neural networks. CoRR (2024)
Atsushi Nitanda, Ryuhei Kikuchi, Shugo Maeda, Denny Wu
Why is parameter averaging beneficial in SGD? An objective smoothing perspective. AISTATS (2024)
Zhichao Wang, Denny Wu, Zhou Fan
Nonlinear spiked covariance matrices and signal propagation in deep neural networks. COLT (2024)
Kazusato Oko, Yujin Song, Taiji Suzuki, Denny Wu
Learning sum of diverse features: computational hardness and efficient gradient-based training for ridge combinations. CoRR (2024)
Jason D. Lee, Kazusato Oko, Taiji Suzuki, Denny Wu
Neural network learns low-dimensional polynomials with SGD near the information-theoretic limit. CoRR (2024)
Alireza Mousavi Hosseini, Denny Wu, Taiji Suzuki, Murat A. Erdogdu
Gradient-Based Feature Learning under Structured Data. NeurIPS (2023)
Taiji Suzuki, Denny Wu, Atsushi Nitanda
Mean-field Langevin dynamics: Time-space discretization, stochastic gradient, and variance reduction. NeurIPS (2023)
Jimmy Ba, Murat A. Erdogdu, Taiji Suzuki, Zhichao Wang, Denny Wu
Learning in the Presence of Low-dimensional Structure: A Spiked Random Matrix Perspective. NeurIPS (2023)
Atsushi Nitanda, Kazusato Oko, Denny Wu, Nobuhito Takenouchi, Taiji Suzuki
Primal and Dual Analysis of Entropic Fictitious Play for Finite-sum Problems. CoRR (2023)
Taiji Suzuki, Atsushi Nitanda, Denny Wu
Uniform-in-time propagation of chaos for the mean-field gradient Langevin dynamics. ICLR (2023)
Taiji Suzuki, Denny Wu, Atsushi Nitanda
Convergence of mean-field Langevin dynamics: Time and space discretization, stochastic gradient, and variance reduction. CoRR (2023)
Taiji Suzuki, Denny Wu, Kazusato Oko, Atsushi Nitanda
Feature learning via mean-field Langevin dynamics: classifying sparse parities and beyond. NeurIPS (2023)
Alireza Mousavi Hosseini, Denny Wu, Taiji Suzuki, Murat A. Erdogdu
Gradient-Based Feature Learning under Structured Data. CoRR (2023)
Atsushi Nitanda, Kazusato Oko, Denny Wu, Nobuhito Takenouchi, Taiji Suzuki
Primal and Dual Analysis of Entropic Fictitious Play for Finite-sum Problems. ICML (2023)
Kazusato Oko, Taiji Suzuki, Atsushi Nitanda, Denny Wu
Particle Stochastic Dual Coordinate Ascent: Exponential convergent algorithm for mean field neural network optimization. ICLR (2022)
Jimmy Ba, Murat A. Erdogdu, Marzyeh Ghassemi, Shengyang Sun, Taiji Suzuki, Denny Wu, Tianzong Zhang
Understanding the Variance Collapse of SVGD in High Dimensions. ICLR (2022)
Jimmy Ba, Murat A. Erdogdu, Taiji Suzuki, Zhichao Wang, Denny Wu, Greg Yang
High-dimensional Asymptotics of Feature Learning: How One Gradient Step Improves the Representation. NeurIPS (2022)
Jimmy Ba, Murat A. Erdogdu, Taiji Suzuki, Zhichao Wang, Denny Wu, Greg Yang
High-dimensional Asymptotics of Feature Learning: How One Gradient Step Improves the Representation. CoRR (2022)
Atsushi Nitanda, Denny Wu, Taiji Suzuki
Convex Analysis of the Mean Field Langevin Dynamics. AISTATS (2022)
Naoki Nishikawa, Taiji Suzuki, Atsushi Nitanda, Denny Wu
Two-layer neural network on infinite dimensional data: global optimization guarantee in the mean-field regime. NeurIPS (2022)
Atsushi Nitanda, Denny Wu, Taiji Suzuki
Convex Analysis of the Mean Field Langevin Dynamics. CoRR (2022)
Atsushi Nitanda, Denny Wu, Taiji Suzuki
Particle Dual Averaging: Optimization of Mean Field Neural Network with Global Convergence Rate Analysis. NeurIPS (2021)
Shun-ichi Amari, Jimmy Ba, Roger Baker Grosse, Xuechen Li, Atsushi Nitanda, Taiji Suzuki, Denny Wu, Ji Xu
When does preconditioning help or hurt generalization? ICLR (2021)
Jimmy Ba, Murat A. Erdogdu, Taiji Suzuki, Denny Wu, Tianzong Zhang
Generalization of Two-layer Neural Networks: An Asymptotic Viewpoint. ICLR (2020)
Denny Wu, Ji Xu
On the Optimal Weighted $\ell_2$ Regularization in Overparameterized Linear Regression. NeurIPS (2020)
Atsushi Nitanda, Denny Wu, Taiji Suzuki
Particle Dual Averaging: Optimization of Mean Field Neural Networks with Global Convergence Rate Analysis. CoRR (2020)
Denny Wu, Ji Xu
On the Optimal Weighted $\ell_2$ Regularization in Overparameterized Linear Regression. CoRR (2020)
Shun-ichi Amari, Jimmy Ba, Roger B. Grosse, Xuechen Li, Atsushi Nitanda, Taiji Suzuki, Denny Wu, Ji Xu
When Does Preconditioning Help or Hurt Generalization? CoRR (2020)
Denny Wu, Hirofumi Kobayashi, Charles Ding, Cheng Lei, Keisuke Goda, Marzyeh Ghassemi
Modeling the Biological Pathology Continuum with HSIC-regularized Wasserstein Auto-encoders. CoRR (2019)
Makoto Yamada, Denny Wu, Yao-Hung Hubert Tsai, Hirofumi Ohta, Ruslan Salakhutdinov, Ichiro Takeuchi, Kenji Fukumizu
Post Selection Inference with Incomplete Maximum Mean Discrepancy Estimator. ICLR (Poster) (2019)
Xuechen Li, Denny Wu, Lester Mackey, Murat A. Erdogdu
Stochastic Runge-Kutta Accelerates Langevin Monte Carlo and Beyond. CoRR (2019)
Yao-Hung Hubert Tsai, Makoto Yamada, Denny Wu, Ruslan Salakhutdinov, Ichiro Takeuchi, Kenji Fukumizu
Selecting the Best in GANs Family: a Post Selection Inference Framework. CoRR (2018)
Denny Wu, Yixiu Zhao, Yao-Hung Hubert Tsai, Makoto Yamada, Ruslan Salakhutdinov
"Dependency Bottleneck" in Auto-encoding Architectures: an Empirical Study. CoRR (2018)
Yao-Hung Hubert Tsai, Denny Wu, Makoto Yamada, Ruslan Salakhutdinov, Ichiro Takeuchi, Kenji Fukumizu
Selecting the Best in GANs Family: a Post Selection Inference Framework. ICLR (Workshop) (2018)