Xiangyi Chen
10 papers · 2019–2025 · 6 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 ↓+2 more ↓ Show less ↑
🗺️ Taxonomy Completionist (18) 🐣 Hot Topic Early Bird 🏃 Academic Marathon · Sprint 🌍 Conference Polyglot · Silver 🌉 Interdisciplinary Bridge · Bronze
🌈
Renaissance Researcher
(5)
💎
Century Club · Bronze
Top co-authors
Research topics
Machine Learning
(8)
Optimization & Theory · Machine Learning
(8)
Mathematics & Optimization
(4)
Optimization
(4)
Artificial Intelligence
(3)
Application Areas
(3)
Deep Learning
(2)
Learning Paradigms
(2)
Learning Types
(2)
Optimization & Theory · Deep Learning
(2)
Computer Science
(1)
Computer Vision
(1)
Security & Privacy
(1)
Core AI
(1)
Differential Privacy
(1)
Keywords
adversarial attack
(3)
zeroth-order optimization
(3)
convergence analysis
(3)
non-convex optimization
(2)
differential privacy
(2)
black-box optimization
(2)
gradient compression
(2)
adaptive gradient method
(2)
distributed learning
(2)
stochastic gradient descent
(2)
gradient clipping
(2)
federated learning
(2)
distributed training
(2)
gradient-free optimization
(2)
distributed optimization
(1)
decentralized optimization
(1)
byzantine robustness
(1)
adversarial training
(1)
deep neural network
(1)
diffusion model
(1)
Papers
DiffFERV: Diffusion-based Facial Editing of Real Videos
IJCAI 2025
Distributed adversarial training to robustify deep neural networks at scale
UAI 2022
On the Convergence of Decentralized Adaptive
Gradient Methods
ACML 2022
Understanding Clipping for Federated Learning: Convergence and Client-Level Differential Privacy
ICML 2022
Distributed Training with Heterogeneous Data: Bridging Median- and Mean-Based Algorithms
NeurIPS 2020
Min-Max Optimization without Gradients: Convergence and Applications to Black-Box Evasion and Poisoning Attacks
ICML 2020
Understanding Gradient Clipping in Private SGD: A Geometric Perspective
NeurIPS 2020
On the Convergence of A Class of Adam-Type Algorithms for Non-Convex Optimization
ICLR 2019
signSGD via Zeroth-Order Oracle
ICLR 2019
ZO-AdaMM: Zeroth-Order Adaptive Momentum Method for Black-Box Optimization
NeurIPS 2019