activity
20192021
most citedContrastively Disentangled Sequential Variational Autoencoder

14 citations · 37 across the 8 of their papers we have counts for

collaborators

10 papers

cs.LG202114 cited

Contrastively Disentangled Sequential Variational Autoencoder

Junwen Bai, Weiran Wang, Carla Gomes

Self-supervised disentangled representation learning is a critical task in sequence modeling. The learnt representations contribute to better model interpretability as well as the…

cs.LG20212 cited

Sparse Bayesian Learning via Stepwise Regression

Sebastian Ament, Carla Gomes

Sparse Bayesian Learning (SBL) is a powerful framework for attaining sparsity in probabilistic models. Herein, we propose a coordinate ascent algorithm for SBL termed Relevance Mat…

math.OC20217 cited

On the Optimality of Backward Regression: Sparse Recovery and Subset Selection

Sebatian Ament, Carla Gomes

Sparse recovery and subset selection are fundamental problems in varied communities, including signal processing, statistics and machine learning. Herein, we focus on an important…

cs.LG2021

HOT-VAE: Learning High-Order Label Correlation for Multi-Label Classification via Attention-Based Variational Autoencoders

Wenting Zhao, Shufeng Kong, Junwen Bai +2

Understanding how environmental characteristics affect bio-diversity patterns, from individual species to communities of species, is critical for mitigating effects of global chang…

cs.LG202111 cited

Evaluating Multi-label Classifiers with Noisy Labels

Wenting Zhao, Carla Gomes

Multi-label classification (MLC) is a generalization of standard classification where multiple labels may be assigned to a given sample. In the real world, it is more common to dea…

cs.LG2021

Low-Precision Reinforcement Learning: Running Soft Actor-Critic in Half Precision

Johan Bjorck, Xiangyu Chen, Christopher De Sa +2

Low-precision training has become a popular approach to reduce compute requirements, memory footprint, and energy consumption in supervised learning. In contrast, this promising ap…