Sejun Park
19 papers · 2015–2025 · 5 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 ↓+5 more ↓ Show less ↑
π Interdisciplinary Bridge Β· Bronze πΊοΈ Taxonomy Completionist (33) π Conference Polyglot Β· Silver π£ Hot Topic Early Bird π Academic Marathon Β· Half
π€
Dynamic Duo
(10)
β
The Questioner
π₯
Unstoppable Β· Bronze
π
Century Club Β· Bronze
ποΈ
Keyword Collector
(94)
Top co-authors
Research topics
Machine Learning
(18)
Optimization & Theory Β· Machine Learning
(15)
Deep Learning
(13)
Architectures
(7)
Artificial Intelligence
(6)
Application Areas
(4)
Core Methods
(4)
Optimization & Theory Β· Deep Learning
(4)
Techniques
(4)
Core AI
(3)
Mathematics & Optimization
(2)
Learning Paradigms Β· Artificial Intelligence
(2)
Learning Paradigms Β· Machine Learning
(2)
Learning Types
(2)
Optimization
(2)
Keywords
neural network
(4)
universal approximation
(3)
generalization bound
(3)
graphical model
(3)
federated learning
(2)
stochastic gradient descent
(2)
representation learning
(2)
approximation theory
(2)
automatic differentiation
(2)
clarke subderivative
(2)
knowledge distillation
(2)
model compression
(2)
activation function
(2)
graph matching
(1)
function approximation
(1)
belief propagation
(1)
ensemble learning
(1)
contrastive learning
(1)
variational inference
(1)
approximate inference
(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
NeurIPS 2024
Minimum width for universal approximation using ReLU networks on compact domain
ICLR 2024
What does automatic differentiation compute for neural networks?
ICLR 2024
Guiding Energy-based Models via Contrastive Latent Variables
ICLR 2023
Neural Networks Efficiently Learn Low-Dimensional Representations with SGD
ICLR 2023
On the Correctness of Automatic Differentiation for Neural Networks with Machine-Representable Parameters
ICML 2023
Towards Understanding Ensemble Distillation in Federated Learning
ICML 2023
Generalization Bounds for Stochastic Gradient Descent via Localized Ξ΅-Covers
NeurIPS 2022
Layer-adaptive Sparsity for the Magnitude-based Pruning
ICLR 2021
Minimum Width for Universal Approximation
ICLR 2021
Provable Memorization via Deep Neural Networks using Sub-linear Parameters
COLT 2021
SmoothMix: Training Confidence-calibrated Smoothed Classifiers for Certified Robustness
NeurIPS 2021
Distribution Aligning Refinery of Pseudo-label for Imbalanced Semi-supervised Learning
NeurIPS 2020
Learning Bounds for Risk-sensitive Learning
NeurIPS 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
NeurIPS 2015