Yuanhan Hu

According to our database, Yuanhan Hu authored at least 8 papers between 2020 and 2024.

Collaborative distances:

• Dijkstra number of four.
• Erdős number of four.

2024

Penalized Overdamped and Underdamped Langevin Monte Carlo Algorithms for Constrained Sampling.

Mert Gürbüzbalaban, Yuanhan Hu, Lingjiong Zhu

J. Mach. Learn. Res., 2024

2023

Cyclic and Randomized Stepsizes Invoke Heavier Tails in SGD than Constant Stepsize.

Mert Gürbüzbalaban, Yuanhan Hu, Umut Simsekli, Lingjiong Zhu

Trans. Mach. Learn. Res., 2023

Cyclic and Randomized Stepsizes Invoke Heavier Tails in SGD.

Mert Gürbüzbalaban, Yuanhan Hu, Umut Simsekli, Lingjiong Zhu

CoRR, 2023

2022

Penalized Langevin and Hamiltonian Monte Carlo Algorithms for Constrained Sampling.

Mert Gürbüzbalaban, Yuanhan Hu, Lingjiong Zhu

CoRR, 2022

Heavy-Tail Phenomenon in Decentralized SGD.

Mert Gürbüzbalaban, Yuanhan Hu, Umut Simsekli, Kun Yuan, Lingjiong Zhu

CoRR, 2022

2021

Decentralized Stochastic Gradient Langevin Dynamics and Hamiltonian Monte Carlo.

Mert Gürbüzbalaban, Xuefeng Gao, Yuanhan Hu, Lingjiong Zhu

J. Mach. Learn. Res., 2021

Fractional moment-preserving initialization schemes for training deep neural networks.

Mert Gürbüzbalaban, Yuanhan Hu

Proceedings of the 24th International Conference on Artificial Intelligence and Statistics, 2021

2020

Fractional moment-preserving initialization schemes for training fully-connected neural networks.

Mert Gürbüzbalaban, Yuanhan Hu

CoRR, 2020