Farzin Haddadpour
6 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 ↓
🌍
Conference Polyglot · Bronze
🌉
Interdisciplinary Bridge · Bronze
🗺️
Taxonomy Completionist
(13)
🐣
Hot Topic Early Bird
📈
Trend Setter
Venues
Top co-authors
Research topics
Keywords
non-convex optimization
(3)
stochastic gradient descent
(3)
distributed optimization
(2)
generalization bound
(2)
communication efficiency
(2)
large-scale learning
(1)
gradient descent
(1)
distribution shift
(1)
excess risk
(1)
model averaging
(1)
derivative-free optimization
(1)
distributionally robust optimization
(1)
gradient compression
(1)
zeroth-order optimization
(1)
distributed stochastic gradient descent
(1)
first-order method
(1)
polyak-lojasiewicz condition
(1)
linear speedup
(1)
data redundancy
(1)
communication round
(1)
Papers
Beyond Lipschitz: Sharp Generalization and Excess Risk Bounds for Full-Batch GD
ICLR 2023
Black-Box Generalization: Stability of Zeroth-Order Learning
NeurIPS 2022
Learning Distributionally Robust Models at Scale via Composite Optimization
ICLR 2022
Federated Learning with Compression: Unified Analysis and Sharp Guarantees
AISTATS 2021
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