Michael Crawshaw
10 papers · 2022–2026 · 4 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 ↑
🌉 Interdisciplinary Bridge · Bronze 🌍 Conference Polyglot · Bronze 🐣 Hot Topic Early Bird 🗺️ Taxonomy Completionist (17) 🤝 Dynamic Duo (10)
💎
Century Club · Bronze
🔥
Unstoppable · Bronze
Venues
Top co-authors
Research topics
Machine Learning
(10)
Optimization & Theory · Machine Learning
(9)
Mathematics & Optimization
(5)
Optimization
(5)
Artificial Intelligence
(4)
Deep Learning
(4)
Learning Paradigms · Artificial Intelligence
(4)
Core Methods
(3)
Optimization & Theory · Deep Learning
(2)
Application Areas
(1)
Architectures
(1)
Learning Paradigms · Machine Learning
(1)
Learning Types
(1)
Keywords
federated learning
(4)
convergence rate
(3)
gradient clipping
(3)
heterogeneous data
(3)
stochastic gradient descent
(2)
logistic regression
(2)
unbounded smoothness
(2)
local gradient descent
(2)
non-convex optimization
(2)
sparse linear regression
(1)
communication efficiency
(1)
dual averaging
(1)
composite optimization
(1)
nuclear norm regularization
(1)
gradient descent
(1)
recurrent neural network
(1)
neural network optimization
(1)
convolutional neural network
(1)
distributed optimization
(1)
generalization
(1)
Papers
Tight Bounds for Logistic Regression with Large Stepsize Gradient Descent in Low Dimension
COLT 2026
Complexity Lower Bounds of Adaptive Gradient Algorithms for Non-convex Stochastic Optimization under Relaxed Smoothness
ICLR 2025
Constant Stepsize Local GD for Logistic Regression: Acceleration by Instability
ICML 2025
Local Steps Speed Up Local GD for Heterogeneous Distributed Logistic Regression
ICLR 2025
Federated Learning under Periodic Client Participation and Heterogeneous Data: A New Communication-Efficient Algorithm and Analysis
NeurIPS 2024
Provable Benefits of Local Steps in Heterogeneous Federated Learning for Neural Networks: A Feature Learning Perspective
ICML 2024
EPISODE: Episodic Gradient Clipping with Periodic Resampled Corrections for Federated Learning with Heterogeneous Data
ICLR 2023
Federated Learning with Client Subsampling, Data Heterogeneity, and Unbounded Smoothness: A New Algorithm and Lower Bounds
NeurIPS 2023
Fast Composite Optimization and Statistical Recovery in Federated Learning
ICML 2022
Robustness to Unbounded Smoothness of Generalized SignSGD
NeurIPS 2022