Juhan Bae
University of Toronto
H-index: 7
North America-Canada
Top articles of Juhan Bae
Can We Remove the Square-Root in Adaptive Gradient Methods? A Second-Order Perspective
arXiv preprint arXiv:2402.03496
2024/2/5
Using Large Language Models for Hyperparameter Optimization
2023/11/8
Studying Large Language Model Generalization with Influence Functions
arXiv preprint arXiv:2308.03296
2023/8/7
Efficient Parametric Approximations of Neural Network Function Space Distance
2023/7/3
Nikita Dhawan
H-Index: 20
Juhan Bae
H-Index: 2
Benchmarking Neural Network Training Algorithms
arXiv preprint arXiv:2306.07179
2023/6/12
Multi-Rate VAE: Train Once, Get the Full Rate-Distortion Curve
2022/12/7
If influence functions are the answer, then what is the question?
Advances in Neural Information Processing Systems
2022/12/6
Juhan Bae
H-Index: 2
Nathan Ng
H-Index: 9
Amortized Proximal Optimization
Advances in Neural Information Processing Systems
2022/12/6
Juhan Bae
H-Index: 2
Methods and Systems for Training an Object Detection Algorithm using Synthetic Images
2021/8/31
On Monotonic Linear Interpolation of Neural Network Parameters
2021/7/1
Analyzing Monotonic Linear Interpolation in Neural Network Loss Landscapes
arXiv preprint arXiv:2104.11044
2021/4/22
CSC 311: Introduction to Machine Learning
2020
Delta-STN: Efficient Bilevel Optimization for Neural Networks using Structured Response Jacobians
Advances in Neural Information Processing Systems
2020
Juhan Bae
H-Index: 2