Publications

Fangshuo Liao, Wenyi Su, Anastasios Kyrillidis (2025). Provable Model-Parallel Distributed Principal Component Analysis with Parallel Deflation. CPAL.

Fangshuo Liao, J. Lyle Kim, Cruz Barnum, Anastasios Kyrillidis (2024). On the Error-Propagation of Inexact Hotelling's Deflation for Principal Component Analysis. ICML.

Fangshuo Liao, Anastasios Kyrillidis (2024). Provable Accelerated Convergence of Nesterov’s Momentum for Deep ReLU Neural Networks. ALT.

Cameron R. Wolfe*, Fangshuo Liao*, Qihan Wang, J. Lyle Kim, Anastasios Kyrillidis (2024). How Much Pre-training Is Enough to Discover a Good Subnetwork?. TMLR.

Zichang Liu, Aditya Desai, Fangshuo Liao, Weitao Wang, Victor Xie, Zhaozhuo Xu, Anastasios Kyrillidis, Anshumali Shrivastava (2023). Scissorhands: Exploiting the Persistence of Importance Hypothesis for LLM KV Cache Compression at Test Time. NeurIPS.

Zheyang Xiong, Fangshuo Liao, Anastasios Kyrillidis (2023). Strong Lottery Ticket Hypothesis with $\epilon$–perturbation. AISTATS.

Qihan Wang*, Chen Dun*, Fangshuo Liao*, Chris Jermaine, Anastasios Kyrillidis (2023). LoFT: Finding Lottery Tickets through Filter-wise Training. AISTATS.

Cameron R. Wolfe*, Jingkang Yang*, Fangshuo Liao*, Arindam Chowdhury, Chen Dun, Artun Bayer, Santiago Segarra, Anastasios Kyrillidis (2023). GIST: Distributed Training for Large-Scale Graph Convolutional Networks. Journal of Applied and Computational Topology, 2023.

Fangshuo Liao, Anastasios Kyrillidis (2022). On the Convergence of Shallow Neural Network Training with Randomly Masked Neurons. TMLR.