Chulhee Yun
~Chulhee_Yun1
17
论文总数
8.5
年均投稿
平均评分
接收情况16/17
会议分布
NeurIPS
7
ICLR
6
ICML
4
发表论文 (17 篇)
202511 篇
5
From Linear to Nonlinear: Provable Weak-to-Strong Generalization through Feature Learning
NeurIPS 2025Poster
4
The Cost of Robustness: Tighter Bounds on Parameter Complexity for Robust Memorization in ReLU Nets
NeurIPS 2025Poster
4
Parameter Expanded Stochastic Gradient Markov Chain Monte Carlo
ICLR 2025Poster
4
Understanding Sharpness Dynamics in NN Training with a Minimalist Example: The Effects of Dataset Difficulty, Depth, Stochasticity, and More
ICML 2025Poster
4
Incremental Gradient Descent with Small Epoch Counts is Surprisingly Slow on Ill-Conditioned Problems
ICML 2025Poster
4
Provable Benefit of Random Permutations over Uniform Sampling in Stochastic Coordinate Descent
ICML 2025Poster
4
Convergence and Implicit Bias of Gradient Descent on Continual Linear Classification
ICLR 2025Poster
4
Does SGD really happen in tiny subspaces?
ICLR 2025Poster
4
Through the River: Understanding the Benefit of Schedule-Free Methods for Language Model Training
NeurIPS 2025Poster
4
Arithmetic Transformers Can Length-Generalize in Both Operand Length and Count
ICLR 2025Poster
4
Lightweight Dataset Pruning without Full Training via Example Difficulty and Prediction Uncertainty
ICML 2025Poster
20246 篇
3
Stochastic Extragradient with Flip-Flop Shuffling & Anchoring: Provable Improvements
ICLR 2024Rejected
5
Provable Benefit of Cutout and CutMix for Feature Learning
NeurIPS 2024Spotlight
4
Stochastic Extragradient with Flip-Flop Shuffling & Anchoring: Provable Improvements
NeurIPS 2024Poster
4
Linear attention is (maybe) all you need (to understand Transformer optimization)
ICLR 2024Poster
4
DASH: Warm-Starting Neural Network Training in Stationary Settings without Loss of Plasticity
NeurIPS 2024Poster
4
Position Coupling: Improving Length Generalization of Arithmetic Transformers Using Task Structure
NeurIPS 2024Poster