Bootstrapping Neural Processes

NeurIPS 2020 Bootstrapping Neural Processes Juho Lee, Yoonho Lee, Jungtaek Kim, Eunho Yang, Sung Ju Hwang, Yee Whye Teh  Unlike in the traditional statistical modeling for which a user typically hand-specify a prior, Neural Processes (NPs) implicitly define a broad class of stoch...

Attribution Preservation in Network Compression for Reliable Network Interpretation

NeurIPS 2020 Attribution Preservation in Network Compression for Reliable Network Interpretation Geondo Park, June Yong Yang, Sung Ju Hwang, Eunho Yang  Neural networks embedded in safety-sensitive applications such as self-driving cars and wearable health monitors rely...

Adversarial Self-Supervised Contrastive Learning

NeurIPS 2020 Adversarial Self-Supervised Contrastive Learning Minseon Kim, Jihoon Tack, Sung Ju Hwang  Existing adversarial learning approaches mostly use class labels to generate adversarial samples that lead to incorrect predictions, which are then used to augment the training ...

Adversarial Neural Pruning with Latent Vulnerability Suppression

ICML 2020 Adversarial Neural Pruning with Latent Vulnerability Suppression Divyam Madaan, Jinwoo Shin, Sung Ju Hwang  Despite the remarkable performance of deep neural networks on various computer vision tasks, they are known to be susceptible to adversarial perturbations, w...

A benchmark study on reliable molecular supervised learning via Bayesian learning

ICML 2020 Workshop on Uncertainty and Robustness in Deep Learning A benchmark study on reliable molecularsupervised learning via Bayesian learning Doyeong Hwang, Grace Lee, Hanseok Jo, Seyoul Yoon, Seongok Ryu  Virtual screening aims to find desirable compounds from chemical libr...

Deep Mixed Effect Composite RNN-GP: A Personalized and Reliable Prediction Model for Healthcare

arXiv 2018 Deep Mixed Effect Composite RNN-GP: A Personalized and Reliable Prediction Model for Healthcare Ingyo Chung, Saehoon Kim, Juho Lee, Sung Ju Hwang, Eunho Yang  We present a personalized and reliable prediction model for healthcare, which can provide individually tailore...

Trimming the ℓ 1 Regularizer: Statistical Analysis, Optimization, and Applications to Deep Learning

ICML 2019 (full oral presentation) Trimming the ℓ 1 Regularizer: Statistical Analysis, Optimization, and Applications to Deep Learning Jihun Yun, Peng Zheng, Aurelie Lozano, Aleksandr Aravkin, Eunho Yang  We study high-dimensional estimators with the trimmed ℓ1 penalty,...

Training CNNs with Selective Allocation of Channels

ICML 2019 Training CNNs with Selective Allocation ofChannels Jongheon Jeong, Jinwoo Shin  Recent progress in deep convolutional neural networks (CNNs) have enabled a simple paradigm of architecture design: larger models typically achieve better accuracy. Due to this, in modern CN...

Towards Deep Amortized Clustering

NeurIPS 2019 Workshop on Sets & Partitions Towards Deep Amortized ClusteringJuho Lee, Yoonho Lee, Yee Whye Teh We tackle amortized clustering, the problem of learning a neural network that can cluster a new dataset with only a few forward passes. We propose a novel learning framework f...

Stochastic Gradient Methods with Block Diagonal Matrix Adaptation

ICML 2019 Stochastic Gradient Methods with Block Diagonal Matrix Adaptation Jihun Yun, Aurelie C. Lozano, Eunho Yang  Adaptive gradient approaches that automatically adjust the learning rate on a per-feature basis have been very popular for training deep networks. This rich class...