Prometheus: Taming Sample and Communication Complexities in Constrained Decentralized Stochastic Bilevel Learning
- Zhuqing Liu
- Xin Zhang
- et al.
- 2023
- ICML 2023
Publications
This is our catalog of publications authored by IBM researchers, in collaboration with the global research community. It’s an ever-growing body of work that shows why IBM is one of the most important contributors to modern computing.
Date
Featured collections
Popular topics
67 results for Songtao Lu
Compressed Decentralized Proximal Stochastic Gradient Method for Nonconvex Composite Problems with Heterogeneous Data
- Yonggui Yan
- Jie Chen
- 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 Stochastic Linearized Augmented Lagrangian Method for Decentralized Bilevel Optimization
- Songtao Lu
- Siliang Zeng
- et al.
- 2022
- NeurIPS 2022
Understanding Benign Overfitting in Gradient-based Meta Learning
- Lisha Chen
- Songtao Lu
- et al.
- 2022
- NeurIPS 2022
A Single-Loop Gradient Descent and Perturbed Ascent Algorithm for Nonconvex Functional Constrained Optimization
- 2022
- ICML 2022
Zeroth-Order Optimization for Composite Problems with Functional Constraints
- Zichong Li
- Pin-Yu Chen
- et al.
- 2022
- AAAI 2022
Adversarial Examples Can Be Effective Data Augmentation for Unsupervised Machine Learning
- Chia-Yi Hsu
- Pin-Yu Chen
- et al.
- 2022
- AAAI 2022
Understanding latent correlation-based multiview learning and self-supervision: An identifiability perspective
- Qi Lyu
- Xiao Fu
- et al.
- 2022
- ICLR 2022
A Text-based Safety Benchmark for Reinforcement Learning Problems
- Ngoc Lan Hoang
- Nicolas Galichet
- et al.
- 2022
- NeurIPS 2022