Fangshuo Liao

According to our database, Fangshuo Liao authored at least 17 papers between 2022 and 2026.

Collaborative distances:

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

2026

AdaPaD: Adaptive Parallel Deflation for PEFT with Self-Correcting Rank Discovery.

Barbara Su, Fangshuo Liao, Anastasios Kyrillidis

CoRR, May, 2026

SGD at the Edge of Stability: The Stochastic Sharpness Gap.

Fangshuo Liao, Afroditi Kolomvaki, Anastasios Kyrillidis

CoRR, April, 2026

Exploiting Low-Rank Structure in Max-K-Cut Problems.

Ria Stevens, Fangshuo Liao, Barbara Su, Jianqiang Li, Anastasios Kyrillidis

CoRR, February, 2026

Convergence Analysis of Two-Layer Neural Networks under Gaussian Input Masking.

Afroditi Kolomvaki, Fangshuo Liao, Evan Dramko, Ziyun Guang, Anastasios Kyrillidis

CoRR, February, 2026

2025

Guided by the Experts: Provable Feature Learning Dynamic of Soft-Routed Mixture-of-Experts.

Fangshuo Liao, Anastasios Kyrillidis

CoRR, October, 2025

One Rank at a Time: Cascading Error Dynamics in Sequential Learning.

Mahtab Alizadeh Vandchali, Fangshuo Liao, Anastasios Kyrillidis

CoRR, May, 2025

Provable Model-Parallel Distributed Principal Component Analysis with Parallel Deflation.

Fangshuo Liao, Wenyi Su, Anastasios Kyrillidis

Proceedings of the Conference on Parsimony and Learning, 2025

2024

GIST: distributed training for large-scale graph convolutional networks.

Cameron R. Wolfe, Jingkang Yang, Fangshuo Liao, Arindam Chowdhury, Chen Dun, Artun Bayer, Santiago Segarra, Anastasios Kyrillidis

J. Appl. Comput. Topol., October, 2024

How Much Pre-training Is Enough to Discover a Good Subnetwork?

Cameron R. Wolfe, Fangshuo Liao, Qihan Wang, Junhyung Lyle Kim, Anastasios Kyrillidis

Trans. Mach. Learn. Res., 2024

On the Error-Propagation of Inexact Hotelling's Deflation for Principal Component Analysis.

Fangshuo Liao, Junhyung Lyle Kim, Cruz Barnum, Anastasios Kyrillidis

Proceedings of the Forty-first International Conference on Machine Learning, 2024

Provable Accelerated Convergence of Nesterov's Momentum for Deep ReLU Neural Networks.

Fangshuo Liao, Anastasios Kyrillidis

Proceedings of the International Conference on Algorithmic Learning Theory, 2024

2023

On the Error-Propagation of Inexact Deflation for Principal Component Analysis.

Fangshuo Liao, Junhyung Lyle Kim, Cruz Barnum, Anastasios Kyrillidis

CoRR, 2023

Accelerated Convergence of Nesterov's Momentum for Deep Neural Networks under Partial Strong Convexity.

Fangshuo Liao, Anastasios Kyrillidis

CoRR, 2023

Scissorhands: Exploiting the Persistence of Importance Hypothesis for LLM KV Cache Compression at Test Time.

Zichang Liu, Aditya Desai, Fangshuo Liao, Weitao Wang, Victor Xie, Zhaozhuo Xu, Anastasios Kyrillidis, Anshumali Shrivastava

Proceedings of the Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, 2023

Strong Lottery Ticket Hypothesis with ε-perturbation.

Zheyang Xiong, Fangshuo Liao, Anastasios Kyrillidis

Proceedings of the International Conference on Artificial Intelligence and Statistics, 2023

LOFT: Finding Lottery Tickets through Filter-wise Training.

Qihan Wang, Chen Dun, Fangshuo Liao, Chris Jermaine, Anastasios Kyrillidis

Proceedings of the International Conference on Artificial Intelligence and Statistics, 2023

2022

On the Convergence of Shallow Neural Network Training with Randomly Masked Neurons.

Fangshuo Liao, Anastasios Kyrillidis

Trans. Mach. Learn. Res., 2022