← Authors

Sejun Park

19 papers · 2015–2025 · 5 conferences · across top CS/AI conferences

Achievements

🐣 Hot Topic Early Bird 🧭 Keyword Pioneer 🌍 Conference Polyglot (5) πŸƒ Academic Marathon (10) 🐝 Cross-Pollinator (14) πŸ—ΊοΈ Taxonomy Completionist (30) πŸŒ‰ Interdisciplinary Bridge 🀝 Dynamic Duo (10) ❓ The Questioner πŸ”₯ Unstoppable (7) πŸ’Ž Century Club (19) πŸ—ƒοΈ Keyword Collector (57)

Conferences

ICLR (6) NIPS (6) ICML (5) AISTATS (1) COLT (1)

Top co-authors

Jinwoo Shin (10) Jaeho Lee (4) Wonyeol Lee (3) Jongheon Jeong (2) Namjun Kim (2) Sungsoo Ahn (2) Murat A Erdogdu (2) Eunho Yang (2) Geonho Hwang (2) Chulhee Yun (2)

Keywords

graphical model (3) neural network (2) generalization bound (2) knowledge distillation (2) federated learning (2) approximate inference (1) distributed learning (1) certified robustness (1) graph matching (1) function approximation (1) semi-supervised learning (1) belief propagation (1) confidence calibration (1) automatic differentiation (1) class imbalance (1) ising model (1) markov chain monte carlo (1) empirical risk minimization (1) nonparametric learning (1) ensemble learning (1)

Papers

Floating-Point Neural Networks Can Represent Almost All Floating-Point Functions ICML 2025
Minimum Width for Universal Approximation using Squashable Activation Functions ICML 2025
A Kernel Perspective on Distillation-based Collaborative Learning NIPS 2024
Minimum width for universal approximation using ReLU networks on compact domain ICLR 2024
What does automatic differentiation compute for neural networks? ICLR 2024
On the Correctness of Automatic Differentiation for Neural Networks with Machine-Representable Parameters ICML 2023
Neural Networks Efficiently Learn Low-Dimensional Representations with SGD ICLR 2023
Towards Understanding Ensemble Distillation in Federated Learning ICML 2023
Guiding Energy-based Models via Contrastive Latent Variables ICLR 2023
Generalization Bounds for Stochastic Gradient Descent via Localized $\varepsilon$-Covers NIPS 2022
Minimum Width for Universal Approximation ICLR 2021
SmoothMix: Training Confidence-calibrated Smoothed Classifiers for Certified Robustness NIPS 2021
Provable Memorization via Deep Neural Networks using Sub-linear Parameters COLT 2021
Layer-adaptive Sparsity for the Magnitude-based Pruning ICLR 2021
Distribution Aligning Refinery of Pseudo-label for Imbalanced Semi-supervised Learning NIPS 2020
Learning Bounds for Risk-sensitive Learning NIPS 2020
Spectral Approximate Inference ICML 2019
Rapid Mixing Swendsen-Wang Sampler for Stochastic Partitioned Attractive Models AISTATS 2017
Minimum Weight Perfect Matching via Blossom Belief Propagation NIPS 2015