Fangshuo Liao

20 papers A* 2A 2B 1Journal 14Unranked 1
YearRankTypeTitle / Venue / Authors
2026 J jnl
Convergence Analysis of Two-Layer Neural Networks under Gaussian Input Masking.
CoRR
Afroditi Kolomvaki, Fangshuo Liao, Evan Dramko, Ziyun Guang, Anastasios Kyrillidis
2026 J jnl
Exploiting Low-Rank Structure in Max-K-Cut Problems.
CoRR
Ria Stevens, Fangshuo Liao, Barbara Su, Jianqiang Li, Anastasios Kyrillidis
2025 J jnl
Guided by the Experts: Provable Feature Learning Dynamic of Soft-Routed Mixture-of-Experts.
CoRR
Fangshuo Liao, Anastasios Kyrillidis
2025 J jnl
One Rank at a Time: Cascading Error Dynamics in Sequential Learning.
CoRR
Mahtab Alizadeh Vandchali, Fangshuo Liao, Anastasios Kyrillidis
2025 — conf
Provable Model-Parallel Distributed Principal Component Analysis with Parallel Deflation.
CPAL
Fangshuo Liao, Wenyi Su, Anastasios Kyrillidis
2025 J jnl
Provable Model-Parallel Distributed Principal Component Analysis with Parallel Deflation.
CoRR
Fangshuo Liao, Wenyi Su, Anastasios Kyrillidis
2024 J jnl
GIST: distributed training for large-scale graph convolutional networks.
J. Appl. Comput. Topol.
Cameron R. Wolfe, Jingkang Yang, Fangshuo Liao, Arindam Chowdhury, Chen Dun, Artun Bayer, Santiago Segarra, Anastasios Kyrillidis
2024 J jnl
How Much Pre-training Is Enough to Discover a Good Subnetwork?
Trans. Mach. Learn. Res.
Cameron R. Wolfe, Fangshuo Liao, Qihan Wang, Junhyung Lyle Kim, Anastasios Kyrillidis
2024 A* conf
On the Error-Propagation of Inexact Hotelling's Deflation for Principal Component Analysis.
ICML
Fangshuo Liao, Junhyung Lyle Kim, Cruz Barnum, Anastasios Kyrillidis
2024 B conf
Provable Accelerated Convergence of Nesterov's Momentum for Deep ReLU Neural Networks.
ALT
Fangshuo Liao, Anastasios Kyrillidis
2023 J jnl
Accelerated Convergence of Nesterov's Momentum for Deep Neural Networks under Partial Strong Convexity.
CoRR
Fangshuo Liao, Anastasios Kyrillidis
2023 A conf
LOFT: Finding Lottery Tickets through Filter-wise Training.
AISTATS
Qihan Wang, Chen Dun, Fangshuo Liao, Chris Jermaine, Anastasios Kyrillidis
2023 J jnl
On the Error-Propagation of Inexact Deflation for Principal Component Analysis.
CoRR
Fangshuo Liao, Junhyung Lyle Kim, Cruz Barnum, Anastasios Kyrillidis
2023 A* conf
Scissorhands: Exploiting the Persistence of Importance Hypothesis for LLM KV Cache Compression at Test Time.
NeurIPS
Zichang Liu, Aditya Desai, Fangshuo Liao, Weitao Wang, Victor Xie, Zhaozhuo Xu, Anastasios Kyrillidis, Anshumali Shrivastava
2023 J jnl
Scissorhands: Exploiting the Persistence of Importance Hypothesis for LLM KV Cache Compression at Test Time.
CoRR
Zichang Liu, Aditya Desai, Fangshuo Liao, Weitao Wang, Victor Xie, Zhaozhuo Xu, Anastasios Kyrillidis, Anshumali Shrivastava
2023 A conf
Strong Lottery Ticket Hypothesis with ε-perturbation.
AISTATS
Zheyang Xiong, Fangshuo Liao, Anastasios Kyrillidis
2022 J jnl
LOFT: Finding Lottery Tickets through Filter-wise Training.
CoRR
Qihan Wang, Chen Dun, Fangshuo Liao, Chris Jermaine, Anastasios Kyrillidis
2022 J jnl
On the Convergence of Shallow Neural Network Training with Randomly Masked Neurons.
Trans. Mach. Learn. Res.
Fangshuo Liao, Anastasios Kyrillidis
2022 J jnl
Strong Lottery Ticket Hypothesis with ε-perturbation.
CoRR
Zheyang Xiong, Fangshuo Liao, Anastasios Kyrillidis
2021 J jnl
On the Convergence of Shallow Neural Network Training with Randomly Masked Neurons.
CoRR
Fangshuo Liao, Anastasios Kyrillidis