Fangshuo Liao

Publication Activity (10 Years)

Years Active: 2021-2024
Publications (10 Years): 12

Top Topics

Training Algorithm

Convergence Speed

Top Venues

Trans. Mach. Learn. Res.

Publications

Cameron R. Wolfe, Fangshuo Liao, Qihan Wang, Junhyung Lyle Kim, Anastasios Kyrillidis
How Much Pre-training Is Enough to Discover a Good Subnetwork? Trans. Mach. Learn. Res. 2024 (2024)
Fangshuo Liao, Anastasios Kyrillidis
Provable Accelerated Convergence of Nesterov's Momentum for Deep ReLU Neural Networks. ALT (2024)
Fangshuo Liao, Anastasios Kyrillidis
Accelerated Convergence of Nesterov's Momentum for Deep Neural Networks under Partial Strong Convexity. CoRR (2023)
Qihan Wang, Chen Dun, Fangshuo Liao, Chris Jermaine, Anastasios Kyrillidis
LOFT: Finding Lottery Tickets through Filter-wise Training. AISTATS (2023)
Zichang Liu, Aditya Desai, Fangshuo Liao, Weitao Wang, Victor Xie, Zhaozhuo Xu, Anastasios Kyrillidis, Anshumali Shrivastava
Scissorhands: Exploiting the Persistence of Importance Hypothesis for LLM KV Cache Compression at Test Time. CoRR (2023)
Zichang Liu, Aditya Desai, Fangshuo Liao, Weitao Wang, Victor Xie, Zhaozhuo Xu, Anastasios Kyrillidis, Anshumali Shrivastava
Scissorhands: Exploiting the Persistence of Importance Hypothesis for LLM KV Cache Compression at Test Time. NeurIPS (2023)
Zheyang Xiong, Fangshuo Liao, Anastasios Kyrillidis
Strong Lottery Ticket Hypothesis with ε-perturbation. AISTATS (2023)
Fangshuo Liao, Junhyung Lyle Kim, Cruz Barnum, Anastasios Kyrillidis
On the Error-Propagation of Inexact Deflation for Principal Component Analysis. CoRR (2023)
Fangshuo Liao, Anastasios Kyrillidis
On the Convergence of Shallow Neural Network Training with Randomly Masked Neurons. Trans. Mach. Learn. Res. 2022 (2022)
Zheyang Xiong, Fangshuo Liao, Anastasios Kyrillidis
Strong Lottery Ticket Hypothesis with ε-perturbation. CoRR (2022)
Qihan Wang, Chen Dun, Fangshuo Liao, Chris Jermaine, Anastasios Kyrillidis
LOFT: Finding Lottery Tickets through Filter-wise Training. CoRR (2022)
Fangshuo Liao, Anastasios Kyrillidis
On the Convergence of Shallow Neural Network Training with Randomly Masked Neurons. CoRR (2021)