This repo contains some of the papers I have read in the past or plan in read in the future. They will be organized in groups of same major topic. In the case a paper was published at a conference, I will write it down.
Implicit Geometric Regularization for Learning Shapes
LaProp: a Better Way to Combine Momentum with Adaptive Gradient
diffGrad: An Optimization Method for Convolutional Neural Networks
Lookahead Optimizer: k steps forward, 1 step back on NIPS 2019
Amortized Inference Regularization on NIPS 2018
BasisVAE: Translation-invariant feature-level clustering with Variational Autoencoders on AISTATS 2020
BIVA: A Very Deep Hierarchy of Latent Variables for Generative Modeling on NeurIPS 2019
The Usual Suspects? Reassessing Blame for VAE Posterior Collapse on ICLR 2020
Lagging Inference Networks and Posterior Collapse in Variational Autoencoders on ICLR 2019
Understanding Posterior Collapse in Generative Latent Variable Models on ICLR 2019
Amortized Population Gibbs Samplers with Neural Sufficient Statistics
Amortized Population Gibbs Samplers with Neural Sufficient Statistics on ICLR 2019
Hierarchical Importance Weighted Autoencoders on ICML 2019
Block Neural Autoregressive Flow
Variationally Inferred Sampling Through a Refined Bound for Probabilistic Programs
Resampled Priors for Variational Autoencoders on AISTATS 2019
Revisiting Auxiliary Latent Variables in Generative Models on ICLR 2019 (workshop)
Importance Weighted Hierarchical Variational Inference
Doubly Semi-Implicit Variational Inference on AISTATS 2019
Unbiased Implicit Variational Inference on AISTATS 2019
Learning Hierarchical Priors in VAEs on NeurIPS 2019
Annealed Importance Weighted Auto-Encoders
Learning Hierarchical Priors in VAEs on NeurIPS 2019)
Structured Semi-Implicit Variational Inference
A Hierarchical Latent Structure for Variational Conversation Modeling
Sequential Attend, Infer, Repeat: Generative Modelling of Moving Objects on NeurIPS 2018
Variational Autoencoders Pursue PCA Directions (by Accident) on CVPR 2019
Preventing Posterior Collapse with delta-VAEs on ICLR 2019
Hyperspherical Variational Auto-Encoders
Variational Rejection Sampling on AISTATS 2018
VAE with a VampPrior on AISTATS 2018
Importance Weighting and Variational Inference on NIPS 2018
Semi-Implicit Variational Inference on ICML 2018
Variational Autoencoder with Implicit Optimal Priors
Variational Saccading: Efficient Inference for Large Resolution Images on BMVC 2019
Semi-Amortized Variational Autoencoders on ICML 2018
Iterative Amortized Inference on ICML 2018
Improving Explorability in Variational Inference with Annealed Variational Objectives on NIPS 2018
Implicit Reparameterization Gradients on NIPS 2018
Adversarial Variational Bayes: Unifying Variational Autoencoders and Generative Adversarial Networks on ICML 2017
Variational Inference using Implicit Distributions
Attend, Infer, Repeat: Fast Scene Understanding with Generative Models on CVPR 2016
Hierarchical Variational Models on JMLR 2016
The Generalized Reparameterization Gradient on NIPS 2016
Reparameterization Gradients through Acceptance-Rejection Sampling Algorithms on AISTATS 2017
Automatic Differentiation Variational Inference on JMLR 2016
Black Box Variational Inference on AISTATS 2014
Recurrent Layer Attention Network on ICLR 2019
Expectation-Maximization Attention Networks for Semantic Segmentation on ICCV 2019
Attention Augmented Convolutional Networks
Attention is all you need for Videos: Self-attention based Video Summarization using Universal Transformers
Is Attention Interpretable? on ACL 2019
Processing Megapixel Images with Deep Attention-Sampling Models on ICML 2019
Saccader: Improving Accuracy of Hard Attention Models for Vision on NeurIPS 2019
You say Normalizing Flows I see Bayesian Networks
Flows for simultaneous manifold learning and density estimation
Exact Information Bottleneck with Invertible Neural Networks: Getting the Best of Discriminative and Generative Modeling
Latent Variable Modelling with Hyperbolic Normalizing Flows
Stochastic Normalizing Flows[1]
Stochastic Normalizing Flows[2]
Neural Spline Flows on NIPS 2019
Learning Likelihoods with Conditional Normalizing Flows
Conditional Flow Variational Autoencoders for Structured Sequence Prediction
FFJORD: Free-form Continuous Dynamics for Scalable Reversible Generative Models on ICLR 2019
Analyzing Inverse Problems with Invertible Neural Networks on ICLR 2019
Block Neural Autoregressive Flow
Neural Autoregressive Flows on ICML 2019 (workshop)
Neural Autoregressive Distribution Estimation on JMLR 2016
Neural Autoregressive Approach to Attention-based Recognition