Mohammad Mahdi Kamani
8 papers · 2019–2023 · 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 ↓+1 more ↓ Show less ↑
🌍 Conference Polyglot · Bronze 🌉 Interdisciplinary Bridge · Bronze 🗺️ Taxonomy Completionist (14) 🐣 Hot Topic Early Bird 🔥 Unstoppable · Bronze
📈
Trend Setter
Venues
Top co-authors
Research topics
Machine Learning
(7)
Optimization & Theory · Machine Learning
(5)
Artificial Intelligence
(4)
Learning Paradigms · Artificial Intelligence
(4)
Deep Learning
(3)
Learning Types
(3)
Mathematics & Optimization
(2)
Application Areas
(2)
Learning Paradigms · Machine Learning
(2)
Optimization
(2)
Optimization & Theory · Deep Learning
(2)
Data Science & Analytics
(1)
Applications
(1)
Architectures
(1)
Keywords
federated learning
(5)
communication efficiency
(3)
distributed optimization
(3)
distributionally robust optimization
(2)
stochastic gradient descent
(2)
periodic averaging
(2)
composite optimization
(1)
distributed learning
(1)
model aggregation
(1)
non-convex optimization
(1)
minimax optimization
(1)
privacy-preserving learning
(1)
empirical risk minimization
(1)
large-scale learning
(1)
distribution shift
(1)
finite-sum optimization
(1)
model averaging
(1)
stochastic gradient
(1)
gradient compression
(1)
relu activation
(1)
Papers
Distributed Personalized Empirical Risk Minimization
NeurIPS 2023
Wyze Rule: Federated Rule Dataset for Rule Recommendation Benchmarking
NeurIPS 2023
Learning Distributionally Robust Models at Scale via Composite Optimization
ICLR 2022
Local SGD Optimizes Overparameterized Neural Networks in Polynomial Time
AISTATS 2022
Federated Learning with Compression: Unified Analysis and Sharp Guarantees
AISTATS 2021
Distributionally Robust Federated Averaging
NeurIPS 2020
Local SGD with Periodic Averaging: Tighter Analysis and Adaptive Synchronization
NeurIPS 2019
Trading Redundancy for Communication: Speeding up Distributed SGD for Non-convex Optimization
ICML 2019