Dongsung Huh
5 papers · 2018–2025 · 3 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+2 more ↓ Show less ↑
🐝 Cross-Pollinator (15) 🏃 Academic Marathon (7) 🌉 Interdisciplinary Bridge 🌍 Conference Polyglot (3) 🧭 Keyword Pioneer
🐣
Hot Topic Early Bird
📈
Trend Setter
Conferences
ICLR (2)
NIPS (2)
ICML (1)
Top co-authors
Keywords
supervised learning
(1)
natural gradient
(1)
gradient descent
(1)
natural gradient descent
(1)
second-order optimization
(1)
spiking neural network
(1)
learning dynamics
(1)
generalization performance
(1)
recurrent network
(1)
deep linear neural network
(1)
curvature correction
(1)
differentiable formulation
(1)
spike-based computation
(1)
Papers
Discovering Group Structures via Unitary Representation Learning
ICLR 2025
ISAAC Newton: Input-based Approximate Curvature for Newton's Method
ICLR 2023
The Missing Invariance Principle found -- the Reciprocal Twin of Invariant Risk Minimization
NIPS 2022
Curvature-corrected learning dynamics in deep neural networks
ICML 2020
Gradient Descent for Spiking Neural Networks
NIPS 2018