Jeremy Bernstein
7 papers · 2018–2025 · 3 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
(10)
🧬
Topic Evolution
Venues
Top co-authors
Research topics
Keywords
learning rate tuning
(2)
gradient compression
(2)
distributed optimization
(1)
neural network optimization
(1)
neural architecture
(1)
majority vote
(1)
gradient descent
(1)
fault tolerance
(1)
communication efficiency
(1)
projected gradient descent
(1)
learning rate
(1)
weight decay
(1)
linear layer
(1)
modular norm
(1)
weight normalization
(1)
gradient lipshitz continuity
(1)
multiplicative weight update
(1)
compositional function
(1)
gradient lipschitz continuity
(1)
learning rate transfer
(1)
Papers
Modular Duality in Deep Learning
ICML 2025
Scalable Optimization in the Modular Norm
NeurIPS 2024
Learning by Turning: Neural Architecture Aware Optimisation
ICML 2021
Learning compositional functions via multiplicative weight updates
NeurIPS 2020
On the distance between two neural networks and the stability of learning
NeurIPS 2020
signSGD with Majority Vote is Communication Efficient and Fault Tolerant
ICLR 2019
signSGD: Compressed Optimisation for Non-Convex Problems
ICML 2018