Publications

This is our catalog of recent publications authored by IBM researchers, in collaboration with the global research community. We’re currently adding our back catalog of more than 110,000 publications. It’s an ever-growing body of work that shows why IBM is one of the most important contributors to modern computing.

Featured collections

Popular topics

Year

18 results for Sijia Liu

How unlabeled data improve generalization in self-training? A one-hidden-layer theoretical analysis
- - Shuai Zhang
  - Meng Weng
  - et al.
- 2022
- ICLR 2022
MEST: Accurate and Fast Memory-Economic Sparse Training Framework on the Edge
- - Geng Yuan
  - Xialong Ma
  - et al.
- 2021
- NeurIPS 2021
Why Lottery Ticket Wins? A Theoretical Perspective of Sample Complexity on Sparse Neural Networks
- - Shuai Zhang
  - Meng Weng
  - et al.
- 2021
- NeurIPS 2021
When does Contrastive Learning Preserve Adversarial Robustness from Pretraining to Finetuning?
- - Lijie Fan
  - Sijia Liu
  - et al.
- 2021
- NeurIPS 2021
Patch-level Routing in Mixture-of-Experts is Provably Sample-efficient for Convolutional Neural Networks
- - Mohammed Nowaz Rabbani Chowdhury
  - Shuai Zhang
  - et al.
- 2023
- ICML 2023
Joint Edge-Model Sparse Learning is Provably Efficient for Graph Neural Networks
- - Shuai Zhang
  - Meng Weng
  - et al.
- 2023
- ICLR 2023
A Theoretical Understanding of Shallow Vision Transformers: Learning, Generalization, and Sample Complexity
- - Hongkang Li
  - Meng Weng
  - et al.
- 2023
- ICLR 2023
Holistic Adversarial Robustness of Deep Learning Models
- - Pin-Yu Chen
  - Sijia Liu
- 2023
- AAAI 2023
Advancing Model Pruning via Bi-level Optimization
- - Yihua Zhang
  - Yuguang Yao
  - et al.
- 2022
- NeurIPS 2022
Data-Efficient Double-Win Lottery Tickets from Robust Pre-training
- - Tianlong Chen
  - Zhenyu Zhang
  - et al.
- 2022
- ICML 2022