Xiaoge Deng （邓晓歌）
Assistant Professor
- dengxg@ustc.edu
- github.com/xiaogdeng
- researchgate.net
- Changsha, Hunan, P.R. China
I am currently an Assistant Professor at the Intelligent Game and Decision Lab in Beijing, China. I received my B.S. degree in Mathematics from the University of Science and Technology of China (USTC) in 2018, and my M.S. and Ph.D. degrees in Computer Science and Technology from the National University of Defense Technology (NUDT) in 2020 and 2024, respectively. During my graduate studies, I was fortunate to be advised by Professors Tao Sun, Dongsheng Li, and Xicheng Lu. My research interests include the optimization of machine learning and AI Agent.
News
- 2025/05 -- Our paper has been accepted by TPAMI
- 2024/12 -- Our paper has been accepted by ICASSP 2025
- 2024/09 -- Our paper has been accepted by NeurIPS 2024
- 2024/05 -- Our paper has been accepted by IEEE Transactions on Big Data
- 2024/04 -- Our paper has been accepted by IJCAI 2024
- 2024/04 -- Our paper has been accepted by Neural Networks
- 2023/07 -- Our paper has been accepted by ECAI 2023
- 2022/12 -- Our paper has been accepted by JSAC-CEDL-22
- 2022/11 -- Our paper has been accepted by AAAI 2023
Publication
Conference Papers
-
Sharpness-Aware Minimization with Adaptive Regularization for Training Deep Neural Networks
Jinping Zou, Xiaoge Deng*, Tao Sun*
IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2025 (CCF B) -
Stability and Generalization of Asynchronous SGD: Sharper Bounds Beyond Lipschitz and Smoothness [pdf][supp][code]
Xiaoge Deng, Tao Sun, Shengwei Li, Dongsheng Li, Xicheng Lu
Advances in Neural Information Processing Systems, NeurIPS 2024 (CCF A) -
Exploring the Inefficiency of Heavy Ball as Momentum Parameter Approaches 1 [pdf][supp][code]
Xiaoge Deng, Tao Sun, Dongsheng Li, Xicheng Lu
33rd International Joint Conference on Artificial Intelligence, IJCAI 2024 (CCF A) -
Normalized Stochastic Heavy Ball with Adaptive Momentum
Ziqing Wen#, Xiaoge Deng#, Tao Sun, Dongsheng Li
26th European Conference on Artificial Intelligence, ECAI 2023 (CCF B) -
Stability-Based Generalization Analysis of the Asynchronous Decentralized SGD [pdf][supp][code]
Xiaoge Deng, Tao Sun, Shengwei Li, Dongsheng Li
Thirty-Seventh AAAI Conference on Artificial Intelligence, AAAI 2023 (CCF A, Oral) -
S2 Reducer: High-Performance Sparse Communication to Accelerate Distributed Deep Learning
Keshi Ge, Yongquan Fu, Yiming Zhang, Zhiquan Lai, Xiaoge Deng, Dongsheng Li
IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2022 (CCF B) -
CASQ: Accelerate Distributed Deep Learning with Sketch-Based Gradient Quantization
Keshi Ge, Yiming Zhang, Yongquan Fu, Zhiquan Lai, Xiaoge Deng, Dongsheng Li
IEEE International Conference on Cluster Computing, CLUSTER 2021 (CCF B) -
PRIAG: Proximal Reweighted Incremental Aggregated Gradient Algorithm for Distributed Optimizations
Xiaoge Deng, Tao Sun, Feng Liu, Feng Huang
International Conference on Algorithms and Architectures for Parallel Processing, ICA3PP 2020
Journal Papers
-
Towards Understanding the Generalizability of Delayed Stochastic Gradient Descent[code]
Xiaoge Deng, Li Shen, Shengwei Li, Tao Sun, Dongsheng Li and Dacheng Tao
IEEE Transactions on Pattern Analysis and Machine Intelligence, 2025 (IF 20.8, CCF A) -
Communication-Efficient Distributed Learning via Sparse and Adaptive Stochastic Gradient[code]
Xiaoge Deng, Dongsheng Li, Tao Sun, Xicheng Lu
IEEE Transactions on Big Data, 2024 (IF 7.2) -
Decentralized Stochastic Sharpness-aware Minimization Algorithm
Simiao Chen#, Xiaoge Deng#, Dongpo Xu, Tao Sun, Dongsheng Li
Neural Networks, 2024 (IF 7.8, CCF B) -
Accelerate Distributed Deep Learning with Cluster-aware Sketch Quantization
Keshi Ge, Yiming Zhang, Yongquan Fu, Zhiquan Lai, Xiaoge Deng, Dongsheng Li
Science China Information Sciences, 2023 (IF 7.3) -
Compressed Collective Sparse-Sketch for Distributed Data-Parallel Training of Deep Learning Models
Keshi Ge, Kai Lu, Yongquan Fu, Xiaoge Deng, Zhiquan Lai, Dongsheng Li
IEEE Journal on Selected Areas in Communications Special Issue on Communication-Efficient Distributed Learning over Networks, JSAC-CEDL-22 (IF 16.4, CCF A) -
SignGD with Error Feedback Meets Lazily Aggregated Technique: Communication-efficient Algorithms for Distributed Learning
Xiaoge Deng, Tao Sun, Feng Liu, Dongsheng Li
Tsinghua Science and Technology, 2022 (IF 6.6) -
A Nonconvex Implementation of Sparse Subspace Clustering: Algorithm and Convergence Analysis
Xiaoge Deng, Tao Sun, Peibing Du, Dongsheng Li
IEEE Access, 2020