Dongsung Huh

According to our database, Dongsung Huh authored at least 12 papers between 2009 and 2026.

Collaborative distances:

• Dijkstra number of four.
• Erdős number of three.

2026

Open Problem: Separating Geometric and Algorithmic Compression via Cayley-Table Completion.

Dongsung Huh

CoRR, May, 2026

Group-Algebraic Tensors: Provably-optimal Equivariant Learning and Physical Symmetry Discovery.

Paulina Hoyos, Shashanka Ubaru, Dongsung Huh, Vasileios Kalantzis, Kenneth L. Clarkson, Misha Elena Kilmer, Haim Avron, Lior Horesh

CoRR, May, 2026

2025

A Theoretical Framework for Discovering Groups and Unitary Representations via Tensor Factorization.

Dongsung Huh, Halyun Jeong

CoRR, November, 2025

Surrogate-based quantification of policy uncertainty in generative flow networks.

Ramón Dineth Nartallo-Kaluarachchi, Robert Manson-Sawko, Shashanka Ubaru, Dongsung Huh, Malgorzata J. Zimon, Lior Horesh, Yoshua Bengio

CoRR, October, 2025

Discovering Group Structures via Unitary Representation Learning.

Dongsung Huh

Proceedings of the Thirteenth International Conference on Learning Representations, 2025

2024

Discovering Symmetry Group Structures via Implicit Orthogonality Bias.

Dongsung Huh

CoRR, 2024

2023

ISAAC Newton: Input-based Approximate Curvature for Newton's Method.

Felix Petersen, Tobias Sutter, Christian Borgelt, Dongsung Huh, Hilde Kuehne, Yuekai Sun, Oliver Deussen

Proceedings of the Eleventh International Conference on Learning Representations, 2023

2022

The Missing Invariance Principle found - the Reciprocal Twin of Invariant Risk Minimization.

Dongsung Huh, Avinash Baidya

Proceedings of the Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022, 2022

2020

Curvature-corrected learning dynamics in deep neural networks.

Dongsung Huh

Proceedings of the 37th International Conference on Machine Learning, 2020

2018

Gradient Descent for Spiking Neural Networks.

Dongsung Huh, Terrence J. Sejnowski

Proceedings of the Advances in Neural Information Processing Systems 31: Annual Conference on Neural Information Processing Systems 2018, 2018

2015

The Vector Space of Convex Curves: How to Mix Shapes.

Dongsung Huh

CoRR, 2015

2009

Real-time motor control using recurrent neural networks.

Dongsung Huh, Emanuel Todorov

Proceedings of the IEEE Symposium on Adaptive Dynamic Programming and Reinforcement Learning, 2009