Ionut-Vlad Modoranu
5 papers · 2021–2025 · 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
🌉
Interdisciplinary Bridge · Bronze
🐣
Hot Topic Early Bird
❓
The Questioner
Venues
Top co-authors
Research topics
Keywords
error feedback
(2)
memory efficiency
(2)
adaptive optimization
(2)
language model training
(1)
adversarial training
(1)
distributed optimization
(1)
neural network optimization
(1)
second-order optimization
(1)
adversarial attack
(1)
convergence guarantee
(1)
gradient compression
(1)
adam optimizer
(1)
inference latency
(1)
gradient information
(1)
adaptive optimizer
(1)
optimal brain surgeon
(1)
neural network
(1)
low-rank compression
(1)
multi-exit neural network
(1)
memory overhead
(1)
Papers
LDAdam: Adaptive Optimization from Low-Dimensional Gradient Statistics
ICLR 2025
Error Feedback Can Accurately Compress Preconditioners
ICML 2024
MicroAdam: Accurate Adaptive Optimization with Low Space Overhead and Provable Convergence
NeurIPS 2024
The Iterative Optimal Brain Surgeon: Faster Sparse Recovery by Leveraging Second-Order Information
NeurIPS 2024
A Panda? No, It's a Sloth: Slowdown Attacks on Adaptive Multi-Exit Neural Network Inference
ICLR 2021