Arsalan Sharifnassab
5 papers · 2019–2025 · 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
🏃
Academic Marathon · Sprint
🌉
Interdisciplinary Bridge · Bronze
🗺️
Taxonomy Completionist
(15)
🐣
Hot Topic Early Bird
Venues
Research topics
Machine Learning
(5)
Optimization & Theory
(5)
Mathematics & Optimization
(3)
Optimization
(3)
Artificial Intelligence
(1)
Deep Learning
(1)
Reinforcement Learning
(1)
Applications
(1)
Learning Paradigms · Artificial Intelligence
(1)
Learning Paradigms · Machine Learning
(1)
Methods
(1)
Techniques
(1)
Keywords
communication efficiency
(2)
distributed optimization
(2)
multi-resolution estimator
(2)
one-shot learning
(2)
parameter estimation
(1)
distributed learning
(1)
loss landscape
(1)
meta-parameters
(1)
gradient-based method
(1)
value estimation
(1)
bellman error
(1)
statistical optimization
(1)
regret
(1)
learning rate
(1)
relu activation
(1)
lower bound
(1)
shallow neural network
(1)
error bound
(1)
first-order optimization
(1)
convex loss function
(1)
Papers
MetaOptimize: A Framework for Optimizing Step Sizes and Other Meta-parameters
ICML 2025
Toward Efficient Gradient-Based Value Estimation
ICML 2023
One-Shot Federated Learning: Theoretical Limits and Algorithms to Achieve Them
JMLR 2021
Bounds on Over-Parameterization for Guaranteed Existence of Descent Paths in Shallow ReLU Networks
ICLR 2020
Order Optimal One-Shot Distributed Learning
NeurIPS 2019