← Authors

Zheng Xu

29 papers · 2016–2025 · 9 conferences · across top CS/AI conferences

Achievements

🐣 Hot Topic Early Bird πŸŒ‰ Interdisciplinary Bridge 🧭 Keyword Pioneer 🌍 Conference Polyglot (9) πŸƒ Academic Marathon (9) 🐝 Cross-Pollinator (8) 🌈 Renaissance Researcher (8) πŸ—ΊοΈ Taxonomy Completionist (43) 🀝 Dynamic Duo (12) πŸ† Grand Slam ❓ The Questioner (2) ⚑ Prolific Year (6) πŸ—ƒοΈ Keyword Collector (102) πŸ”₯ Unstoppable (10) πŸ’Ž Century Club (29) πŸš€ Conference Pioneer πŸ“ˆ Trend Setter

Conferences

ICML (10) NIPS (6) EMNLP (3) ICLR (3) ACL (2) CVPR (2) AAAI (1) AISTATS (1) NAACL (1)

Top co-authors

Tom Goldstein (12) Peter Kairouz (5) Sewoong Oh (4) Gavin Taylor (4) Christoph Studer (4) Hao Li (3) Gauri Joshi (3) Yanxiang Zhang (3) Satyen Kale (2) Christopher A. Choquette-Choo (2)

Research topics

Differential Privacy (1) Privacy (1)

Keywords

differential privacy (7) federated learning (7) stochastic gradient descent (4) large language model (3) neural network optimization (2) adversarial training (2) skip connection (2) adversarial attack (2) language model (2) model compression (2) convex optimization (2) convergence analysis (2) alternating direction method of multiplier (2) domain adaptation (1) non-convex optimization (1) model quantization (1) nonconvex optimization (1) neural network training (1) convergence acceleration (1) batch normalization (1)

Papers

Synthesizing and Adapting Error Correction Data for Mobile Large Language Model Applications ACL 2025
Synthesizing Privacy-Preserving Text Data via Finetuning *without* Finetuning Billion-Scale LLMs ICML 2025
Debiasing Federated Learning with Correlated Client Participation ICLR 2025
Can Public Large Language Models Help Private Cross-device Federated Learning? NAACL 2024
Heterogeneous LoRA for Federated Fine-tuning of On-Device Foundation Models EMNLP 2024
User Inference Attacks on Large Language Models EMNLP 2024
A Hassle-free Algorithm for Strong Differential Privacy in Federated Learning Systems EMNLP 2024
Improved Communication-Privacy Trade-offs in $L_2$ Mean Estimation under Streaming Differential Privacy ICML 2024
Safe and Robust Subgame Exploitation in Imperfect Information Games ICML 2024
Privacy-Preserving Instructions for Aligning Large Language Models ICML 2024
(Amplified) Banded Matrix Factorization: A unified approach to private training NIPS 2023
Federated Learning of Gboard Language Models with Differential Privacy ACL 2023
Learning To Generate Image Embeddings With User-Level Differential Privacy CVPR 2023
Beyond Uniform Lipschitz Condition in Differentially Private Optimization ICML 2023
On the Convergence of Federated Averaging with Cyclic Client Participation ICML 2023
Efficient Subgame Refinement for Extensive-form Games NIPS 2023
Diurnal or Nocturnal? Federated Learning of Multi-branch Networks from Periodically Shifting Distributions ICLR 2022
GradInit: Learning to Initialize Neural Networks for Stable and Efficient Training NIPS 2021
Practical and Private (Deep) Learning Without Sampling or Shuffling ICML 2021
Universal Adversarial Training AAAI 2020
The Impact of Neural Network Overparameterization on Gradient Confusion and Stochastic Gradient Descent ICML 2020
Adversarial training for free! NIPS 2019
Visualizing the Loss Landscape of Neural Nets NIPS 2018
Stabilizing Adversarial Nets with Prediction Methods ICLR 2018
Adaptive ADMM with Spectral Penalty Parameter Selection AISTATS 2017
Training Quantized Nets: A Deeper Understanding NIPS 2017
Adaptive Consensus ADMM for Distributed Optimization ICML 2017
Adaptive Relaxed ADMM: Convergence Theory and Practical Implementation CVPR 2017
Training Neural Networks Without Gradients: A Scalable ADMM Approach ICML 2016