Dachao Lin

Publication Activity (10 Years)

Years Active: 2010-2024
Publications (10 Years): 19

Top Topics

Convergence Analysis

Number Of Hidden Units

Multilayer Neural Networks

Top Venues

Publications

Jing Li, Zhijie Sun, Dachao Lin, Xuan He, Yi Lin, Binfan Zheng, Li Zeng, Rongqian Zhao, Xin Chen
LocMoE+: Enhanced Router with Token Feature Awareness for Efficient LLM Pre-Training. CoRR (2024)
Dachao Lin, Yuze Han, Haishan Ye, Zhihua Zhang
Stochastic Distributed Optimization under Average Second-order Similarity: Algorithms and Analysis. CoRR (2023)
Haishan Ye, Dachao Lin, Xiangyu Chang, Zhihua Zhang
Towards explicit superlinear convergence rate for SR1. Math. Program. 199 (1) (2023)
Dachao Lin, Yuze Han, Haishan Ye, Zhihua Zhang
Stochastic Distributed Optimization under Average Second-order Similarity: Algorithms and Analysis. NeurIPS (2023)
Dachao Lin, Ruoyu Sun, Zhihua Zhang
On the landscape of one-hidden-layer sparse networks and beyond. Artif. Intell. 309 (2022)
Kun Chen, Dachao Lin, Zhihua Zhang
Global Convergence Analysis of Deep Linear Networks with A One-neuron Layer. CoRR (2022)
Dachao Lin, Zhihua Zhang
On the Convergence of Policy in Unregularized Policy Mirror Descent. CoRR (2022)
Kun Chen, Dachao Lin, Zhihua Zhang
On Non-local Convergence Analysis of Deep Linear Networks. ICML (2022)
Dachao Lin, Haishan Ye, Zhihua Zhang
Explicit Convergence Rates of Greedy and Random Quasi-Newton Methods. J. Mach. Learn. Res. 23 (2022)
Haishan Ye, Dachao Lin, Zhihua Zhang
Greedy and Random Broyden's Methods with Explicit Superlinear Convergence Rates in Nonlinear Equations. CoRR (2021)
Dachao Lin, Haishan Ye, Zhihua Zhang
Greedy and Random Quasi-Newton Methods with Faster Explicit Superlinear Convergence. NeurIPS (2021)
Dachao Lin, Ruoyu Sun, Zhihua Zhang
Faster Directional Convergence of Linear Neural Networks under Spherically Symmetric Data. NeurIPS (2021)
Guangzeng Xie, Hao Jin, Dachao Lin, Zhihua Zhang
Meta-Regularization: An Approach to Adaptive Choice of the Learning Rate in Gradient Descent. CoRR (2021)
Dachao Lin, Zhihua Zhang
Directional Convergence Analysis under Spherically Symmetric Distribution. CoRR (2021)
Dachao Lin, Peiqin Sun, Guangzeng Xie, Shuchang Zhou, Zhihua Zhang
Optimal Quantization for Batch Normalization in Neural Network Deployments and Beyond. CoRR (2020)
Dachao Lin, Ruoyu Sun, Zhihua Zhang
Landscape of Sparse Linear Network: A Brief Investigation. CoRR (2020)
Hao Jin, Dachao Lin, Zhihua Zhang
Towards Better Generalization: BP-SVRG in Training Deep Neural Networks. CoRR (2019)
Mo Zhou, Tianyi Liu, Yan Li, Dachao Lin, Enlu Zhou, Tuo Zhao
Towards Understanding the Importance of Noise in Training Neural Networks. CoRR (2019)
Mo Zhou, Tianyi Liu, Yan Li, Dachao Lin, Enlu Zhou, Tuo Zhao
Toward Understanding the Importance of Noise in Training Neural Networks. ICML (2019)
Jinshun Wu, Dachao Lin, Genyin Cheng, Weijie Zhang
Application research of comprehensive evaluation based on the theory of unascertainty measure. FSKD (2010)