Juhan Bae
Introduction
I am a PhD student in the Machine Learning Group at the University of Toronto and the Vector Institute, supervised by Roger Grosse. I received my HBSc in computer science and statistics from the same university in 2019. I previously interned at Anthropic and Microsoft Research.
I'm interested in understanding wide range of applications in deep learning. I'm currently working on hyperparameter optimization, optimization, and interpretability of deep learning.
Publications
[T12] Studying Large Language Model Generalization with Influence Functions
arXiv 2023
Paper Blog
[T11] Benchmarking Neural Network Training Algorithms
arXiv 2023
Paper Code
[C10] Efficient Parametric Approximations of Neural Network Function Space Distance
ICML 2023
Paper Code
[C9] Multi-Rate VAE: Train Once, Get the Full Rate-Distortion Curve
ICLR 2023 (Oral Presentation)
Paper Code
[C8] If Influence Functions are the Answer, Then What is the Question?
NeurIPS 2022
Paper Code 1 Code 2
[C7] Amortized Proximal Optimization
NeurIPS 2022
Paper Code
[C6] Analyzing Monotonic Linear Interpolation in Neural Network Loss Landscapes
ICML 2021
Paper Code
[C5] Delta-STN: Efficient Bilevel Optimization for Neural Networks using Structured Response Jacobians
NeurIPS 2020
Paper Code
[W4] On Monotonic Linear Interpolation of Neural Network Parameters
NeurIPS 2020, Optimization for Machine Learning Workshop
Paper Code
[W3] Eigenvalue Corrected Noisy Natural Gradient
NeurIPS 2019, Bayesian Deep Learning Workshop
Paper Code
[C2] Fast 6DOF Pose Estimation with Synthetic Textureless CAD Model for Mobile Applications
ICIP 2019
Paper
[W1] Learnable Pooling Methods for Video Classification
ECCV 2018, Workshop on YouTube-8M Large-Scale Video Understanding (Oral Presentation)
Paper Code
Teaching