Variational Inference

BasisDeVAE: Interpretable Simultaneous Dimensionality Reduction and Feature-Level Clustering with Derivative-Based Variational Autoencoders ICML 2021 Bayesian Deep Learning via Subnetwork Inference ICML 2021 Bayesian Dynamic Mode Decomposition with Variational Matrix Factorization AAAI 2021 Bayesian Structural Adaptation for Continual Learning ICML 2021 Capturing Uncertainty in Unsupervised GPS Trajectory Segmentation Using Bayesian Deep Learning AAAI 2021 CARMS: Categorical-Antithetic-REINFORCE Multi-Sample Gradient Estimator NeurIPS 2021 Causal Hidden Markov Model for Time Series Disease Forecasting CVPR 2021 Challenging the Semi-Supervised VAE Framework for Text Classification EMNLP 2021 Collapsed Variational Bounds for Bayesian Neural Networks NeurIPS 2021 Composing Normalizing Flows for Inverse Problems ICML 2021 Compositional Modeling of Nonlinear Dynamical Systems with ODE-based Random Features NeurIPS 2021 Conformal Bayesian Computation NeurIPS 2021 Continuous-time edge modelling using non-parametric point processes NeurIPS 2021 Coupled Gradient Estimators for Discrete Latent Variables NeurIPS 2021 Cross-structural Factor-topic Model: Document Analysis with Sophisticated Covariates ACML 2021 De-Confounded Variational Encoder-Decoder for Logical Table-to-Text Generation ACL 2021 De-randomizing MCMC dynamics with the diffusion Stein operator NeurIPS 2021 Differentiable Annealed Importance Sampling and the Perils of Gradient Noise NeurIPS 2021 Disentangling Generative Factors in Natural Language with Discrete Variational Autoencoders EMNLP 2021 Domain Generalization under Conditional and Label Shifts via Variational Bayesian Inference IJCAI 2021 Estimating High Order Gradients of the Data Distribution by Denoising NeurIPS 2021 Explaining A Black-box By Using A Deep Variational Information Bottleneck Approach AAAI 2021 Farewell to Mutual Information: Variational Distillation for Cross-Modal Person Re-Identification CVPR 2021 Fast Bayesian Inference for Gaussian Cox Processes via Path Integral Formulation NeurIPS 2021 Flow-Based Kernel Prior With Application to Blind Super-Resolution CVPR 2021