Jaehoon Lee | DeepAI

AI Chat

Featured Co-authors

Radu Timofte
174 publications
Chao Li
169 publications
Jing Liu
126 publications
Cewu Lu
119 publications
Yuan Cao
85 publications
Martin Danelljan
83 publications
Amin Karbasi
77 publications
Jascha Sohl-Dickstein
68 publications
Hua Wang
46 publications
Noseong Park
46 publications
Simon Kornblith
38 publications

∙ 09/15/2023

Replacing softmax with ReLU in Vision Transformers

Previous research observed accuracy degradation when replacing the atten...

0 Mitchell Wortsman, et al. ∙

∙ 08/29/2023

MadSGM: Multivariate Anomaly Detection with Score-based Generative Models

The time-series anomaly detection is one of the most fundamental tasks f...

0 Haksoo Lim, et al. ∙

∙ 06/27/2023

Precursor-of-Anomaly Detection for Irregular Time Series

Anomaly detection is an important field that aims to identify unexpected...

0 Sheo Yon Jhin, et al. ∙

∙ 03/09/2023

Kernel Regression with Infinite-Width Neural Networks on Millions of Examples

Neural kernels have drastically increased performance on diverse and non...

0 Ben Adlam, et al. ∙

∙ 11/22/2022

Time Series Forecasting with Hypernetworks Generating Parameters in Advance

Forecasting future outcomes from recent time series data is not easy, es...

0 Jaehoon Lee, et al. ∙

∙ 09/09/2022

Fast Neural Kernel Embeddings for General Activations

Infinite width limit has shed light on generalization and optimization a...

0 Insu Han, et al. ∙

∙ 04/19/2022

LORD: Lower-Dimensional Embedding of Log-Signature in Neural Rough Differential Equations

The problem of processing very long time-series data (e.g., a length of ...

0 Jaehoon Lee, et al. ∙

∙ 04/19/2022

EXIT: Extrapolation and Interpolation-based Neural Controlled Differential Equations for Time-series Classification and Forecasting

Deep learning inspired by differential equations is a recent research tr...

0 Sheo Yon Jhin, et al. ∙

∙ 02/08/2022

Invertible Tabular GANs: Killing Two Birds with OneStone for Tabular Data Synthesis

Tabular data synthesis has received wide attention in the literature. Th...

0 Jaehoon Lee, et al. ∙

∙ 07/27/2021

Dataset Distillation with Infinitely Wide Convolutional Networks

The effectiveness of machine learning algorithms arises from being able ...

0 Timothy Nguyen, et al. ∙

∙ 05/31/2021

OCT-GAN: Neural ODE-based Conditional Tabular GANs

Synthesizing tabular data is attracting much attention these days for va...

0 Jayoung Kim, et al. ∙

∙ 02/12/2021

Explaining Neural Scaling Laws

The test loss of well-trained neural networks often follows precise powe...

0 Yasaman Bahri, et al. ∙

∙ 11/11/2020

Towards NNGP-guided Neural Architecture Search

The predictions of wide Bayesian neural networks are described by a Gaus...

6 Daniel S. Park, et al. ∙

∙ 10/30/2020

Dataset Meta-Learning from Kernel Ridge-Regression

One of the most fundamental aspects of any machine learning algorithm is...

29 Timothy Nguyen, et al. ∙

∙ 10/14/2020

Exploring the Uncertainty Properties of Neural Networks' Implicit Priors in the Infinite-Width Limit

Modern deep learning models have achieved great success in predictive ac...

7 Ben Adlam, et al. ∙

∙ 07/31/2020

Finite Versus Infinite Neural Networks: an Empirical Study

We perform a careful, thorough, and large scale empirical study of the c...

49 Jaehoon Lee, et al. ∙

∙ 07/15/2020

Data-Efficient Deep Learning Method for Image Classification Using Data Augmentation, Focal Cosine Loss, and Ensemble

In general, sufficient data is essential for the better performance and ...

28 Byeongjo Kim, et al. ∙

∙ 05/05/2020

NTIRE 2020 Challenge on Video Quality Mapping: Methods and Results

This paper reviews the NTIRE 2020 challenge on video quality mapping (VQ...

2 Dario Fuoli, et al. ∙

∙ 01/21/2020

On the infinite width limit of neural networks with a standard parameterization

There are currently two parameterizations used to derive fixed kernels c...

13 Jascha Sohl-Dickstein, et al. ∙

∙ 12/05/2019

Neural Tangents: Fast and Easy Infinite Neural Networks in Python

Neural Tangents is a library designed to enable research into infinite-w...

14 Roman Novak, et al. ∙

∙ 10/11/2019

On Empirical Comparisons of Optimizers for Deep Learning

Selecting an optimizer is a central step in the contemporary deep learni...

0 Dami Choi, et al. ∙

∙ 03/11/2019

Physics Enhanced Artificial Intelligence

We propose that intelligently combining models from the domains of Artif...

0 Patrick O'Driscoll, et al. ∙

∙ 02/18/2019

Wide Neural Networks of Any Depth Evolve as Linear Models Under Gradient Descent

A longstanding goal in deep learning research has been to precisely char...

0 Jaehoon Lee, et al. ∙

∙ 11/08/2018

Measuring the Effects of Data Parallelism on Neural Network Training

Recent hardware developments have made unprecedented amounts of data par...

0 Christopher J. Shallue, et al. ∙

∙ 10/11/2018

Bayesian Convolutional Neural Networks with Many Channels are Gaussian Processes

There is a previously identified equivalence between wide fully connecte...

18 Roman Novak, et al. ∙

∙ 11/01/2017

Deep Neural Networks as Gaussian Processes

A deep fully-connected neural network with an i.i.d. prior over its para...

0 Jaehoon Lee, et al. ∙

Are you a researcher?
Expose your work
to one of the largest
A.I. communities in the world