Xinwei Zhang
10 papers · 2022–2025 · 3 venues · across top CS/AI venues
Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.
Achievements
Jump to papers ↓+1 more ↓ Show less ↑
🌍 Conference Polyglot · Bronze 🌉 Interdisciplinary Bridge · Bronze 🗺️ Taxonomy Completionist (23) 👑 Triple Crown 💎 Century Club · Bronze
🗃️
Keyword Collector
(54)
Venues
Top co-authors
Research topics
Machine Learning
(9)
Optimization & Theory · Machine Learning
(7)
Deep Learning
(6)
Artificial Intelligence
(4)
Security & Privacy
(4)
Application Areas
(4)
Differential Privacy
(4)
Learning Paradigms · Artificial Intelligence
(3)
Learning Types · Deep Learning
(3)
Optimization & Theory · Deep Learning
(3)
Core AI
(2)
Learning Paradigms · Machine Learning
(2)
Learning Types · Machine Learning
(2)
Mathematics & Optimization
(1)
Architectures
(1)
Keywords
differential privacy
(4)
convergence analysis
(3)
stochastic gradient descent
(3)
federated learning
(3)
gradient clipping
(2)
neural network
(2)
gaussian processes
(1)
deep learning
(1)
computer vision
(1)
privacy preservation
(1)
language model
(1)
distributed optimization
(1)
kalman filter
(1)
stochastic control
(1)
model pretraining
(1)
data heterogeneity
(1)
memory efficiency
(1)
linear convergence
(1)
bayesian optimization
(1)
self-supervised learning
(1)
Papers
Addax: Utilizing Zeroth-Order Gradients to Improve Memory Efficiency and Performance of SGD for Fine-Tuning Language Models
ICLR 2025
DiSK: Differentially Private Optimizer with Simplified Kalman Filter for Noise Reduction
ICLR 2025
Boundary Exploration for Bayesian Optimization With Unknown Physical Constraints
ICML 2024
Differentially Private SGD Without Clipping Bias: An Error-Feedback Approach
ICLR 2024
DOPPLER: Differentially Private Optimizers with Low-pass Filter for Privacy Noise Reduction
NeurIPS 2024
Pre-training Differentially Private Models with Limited Public Data
NeurIPS 2024
FedAvg Converges to Zero Training Loss Linearly for Overparameterized Multi-Layer Neural Networks
ICML 2023
A Stochastic Multi-Rate Control Framework For Modeling Distributed Optimization Algorithms
ICML 2022
Grow and Merge: A Unified Framework for Continuous Categories Discovery
NeurIPS 2022
Understanding Clipping for Federated Learning: Convergence and Client-Level Differential Privacy
ICML 2022