(발표 자료) Flow based model (Normalizing Flow)
OWOP(One Week One Paper) paper reading 스터디
Bayesian NN & Variational Inference
(발표 자료) Stochastic Variational Inference & Variational Auto Encoder
OWOP(One Week One Paper) paper reading 스터디
96.Learnable Bernoulli Dropout for Bayesian Deep Learning
Paper Review by Seunghan Lee
95.Multiplicative Normalizing Flows for Variational Bayesian Neural Networks
Paper Review by Seunghan Lee
93.Learning Deep Latent Gaussian Models with Markov Chain Monte Carlo
Paper Review by Seunghan Lee
92.Auxiliary Variational MCMC
Paper Review by Seunghan Lee
91.Neural Adaptive Sequential Monte Carlo
Paper Review by Seunghan Lee
90.Sequential Monte Carlo
Paper Review by Seunghan Lee
89.Markovian Score Climbing ; Variational Inference with KL(p,q)
Paper Review by Seunghan Lee
88.Liberty or Depth ; Deep BNN do not need complex weight posterior approximation
Paper Review by Seunghan Lee
87.Flexible MFVI using mixtures of non-overlapping exponential families
Paper Review by Seunghan Lee
86.Importance Weighted Hierarchical Variational Inference
Paper Review by Seunghan Lee
85.A Simple Baseline for Bayesian Uncertainty in Deep Learning
Paper Review by Seunghan Lee
84.Averaging Weights Leads to Wider Optima and Better Generalization
Paper Review by Seunghan Lee
83.Divide And Couple ; Using Monte Carlo Variational Objectives for Posterior Approximation
Paper Review by Seunghan Lee
82.Variational Denoising Network ; Toward Blind Noise Modeling and Removal
Paper Review by Seunghan Lee
81.Sparse Variational Inference ; Bayesian Coresets from Scrath
Paper Review by Seunghan Lee
80.Overdispersed Black-Box Variational Inference
Paper Review by Seunghan Lee
79.Robust Inference with Variational Bayes
Paper Review by Seunghan Lee
78.On Modern Deep Learning and Variational Inference
Paper Review by Seunghan Lee
77.Variational Inference for Nonparametric Bayesian Quantile Regression
Paper Review by Seunghan Lee
76.Efficient Variational Inference for Gaussian Process Regression Networks
Paper Review by Seunghan Lee
75.Variational Inference for Dirichlet Process Mixture
Paper Review by Seunghan Lee
74.IntroVAE, Introspective Variational Autoencoders for Photographic Image SynthesisNatural Gradient
Paper Review by Seunghan Lee
73.SLANG, Fast Structured Covariance Approximations for Bayesian Deep Learning with Natural Gradient
Paper Review by Seunghan Lee
72.Importance Weighting and Variational Inference
Paper Review by Seunghan Lee
71.DropMax, Adaptive Variational Softmax
Paper Review by Seunghan Lee
70.Bayesian Adversarial Learning
Paper Review by Seunghan Lee
69.Improving Explorability in Variational Inference with Annealed Variational Objectives
Paper Review by Seunghan Lee
68.Coupled Variational Bayes via Optimization Embedding
Paper Review by Seunghan Lee
67.Using Large Ensembles of Control Variates for Variational Inference
Paper Review by Seunghan Lee
66.Variational Inference with Tail-Adaptive f-Divergence
Paper Review by Seunghan Lee
65.Hamiltonian Variational Auto-Encoder
Paper Review by Seunghan Lee
64.Wasserstein Variational Inference (NeurIPS 2018)
Paper Review by Seunghan Lee
63.Discretely Relaxing Continuous Variables for tractable Variational Inference (NeurIPS 2018)
Paper Review by Seunghan Lee
62.Variational Bayesian Monte Carlo (NeurIPS 2018)
Paper Review by Seunghan Lee
60.Hierarchical Variational Models (2015)
Paper Review by Seunghan Lee
59.Copula Variational Inference (2015)
Paper Review by Seunghan Lee
58.Stochastic Backpropagation and Approximate Inference in Deep Generative Models (2014)
Paper Review by Seunghan Lee
57.Structured Stochastic Variational Inference (2014)
Paper Review by Seunghan Lee
56.Smoothed Gradients for Stochastic Variational Inference (2014)
Paper Review by Seunghan Lee
55.Neural Variational Inference and Learning in Belief Networks (2014)
Paper Review by Seunghan Lee
54.Doubly Stochastic Variational Bayes for non-Conjugate Inference (2014)
Paper Review by Seunghan Lee
53.Auto-Encoding Variational Bayes (2014)
Paper Review by Seunghan Lee
52.Variational Inference in Nonconjugate Models (2013)
Paper Review by Seunghan Lee
51.Black Box Variational Inference (2013)
Paper Review by Seunghan Lee
50.Variational Bayesian Inference with Stochastic Search (2012)
Paper Review by Seunghan Lee
49.Nonparametric Variational Inference (2012)
Paper Review by Seunghan Lee
48.Normalizing Flows for Probabilistic Modeling and Inference (2019)
Paper Review by Seunghan Lee
47.Normalizing Flows ; An Introduction and Review of Current Methods (2020)
Paper Review by Seunghan Lee
46.f-VAEs ; Improve VAEs with Conditional Flows
Paper Review by Seunghan Lee
45.Advances in Variational Inference
Paper Review by Seunghan Lee
44.Variational Inference ; A Review for Statisticians
Paper Review by Seunghan Lee
43.A Theoretically Grounded Application of Dropout in Recurrent Neural Networks (2016)
Paper Review by Seunghan Lee
42.A Comprehensive guide to Bayesian Convolutional Neural Network with Variational Inference (2019)
Paper Review by Seunghan Lee
41.Neural Variational Inference for Text Processing (2016)
Paper Review by Seunghan Lee
40.Topic Modeling in Embedding Spaces (2019)
Paper Review by Seunghan Lee
39.Autoencoding Variational Inference for Topic Models (2017)
Paper Review by Seunghan Lee
38.Practical Deep Learning with Bayesian Principles (2019)
Paper Review by Seunghan Lee
37.Adversarial Autoencoders (2016)
Paper Review by Seunghan Lee
36.Gaussian Processes for Big Data (2013)
Paper Review by Seunghan Lee
35.A Stochastic Decoder for Neural Machine Translation (2018)
Paper Review by Seunghan Lee
34.Masked Autoregressive Flow for Density Estimation (2017)
Paper Review by Seunghan Lee
33.Improved Variational Inference with Inverse Autoregressive Flow (2016)
Paper Review by Seunghan Lee
32.MADE_Masked Autoencoder for Distribution Estimation (2015)
Paper Review by Seunghan Lee
28.Glow ; Generative Flow with Invertible 1x1 Convolutions (2018)
Paper Review by Seunghan Lee
27.Density Estimation using Real NVP (2017)
Paper Review by Seunghan Lee
26.Variational Inference with Normalizing Flows (2016)
Paper Review by Seunghan Lee
25.Non-linear Independent Components Estimation (NICE) (2014)
Paper Review by Seunghan Lee
24.A Contrastive Divergence for Combining Variational Inference and MCMC
Paper Review by Seunghan Lee
23.Unbiased Implicit Variational Inference (2019)
Paper Review by Seunghan Lee
22.Semi-Implicit Variational Inference (2018)
Paper Review by Seunghan Lee
21.Variational Inference using Implicit Distributions (2017)
Paper Review by Seunghan Lee
20-3.Uncertainty in Deep Learning (2016)
Paper Review by Seunghan Lee
20-2.Uncertainty in Deep Learning (2016)
Paper Review by Seunghan Lee
20-1.Uncertainty in Deep Learning (2016)
Paper Review by Seunghan Lee
19.Relevance Vector Machine Explained (2010)
Paper Review by Seunghan Lee
18.Variational Dropout Sparsifies Deep Neural Networks (2017)
Paper Review by Seunghan Lee
17.Dropout as Bayesian Approximation (2016)
Paper Review by Seunghan Lee
16.Variational Dropout and Local Reparameterization Trick (2015)
Paper Review by Seunghan Lee
15.Fast Dropout Training (2013)
Paper Review by Seunghan Lee
14.Simple and Scalable Predictive Uncertainty Estimation using Deep Ensembles (2017)
Paper Review by Seunghan Lee
13.Bayesian Uncertainty Estimation for Batch Normalized Deep Networks (2018)
Paper Review by Seunghan Lee
12.Representing Inferential Uncertainty in Deep Neural Networks through Sampling (2017)
Paper Review by Seunghan Lee
11.Deep Neural Networks as Gaussian Processes (2018)
Paper Review by Seunghan Lee
10.Computing with Infinite Networks (1997)
Paper Review by Seunghan Lee
(TFP) 11.Normalizing Flows - MAF, IAF, RealNVP
NF, AF, MAF, IAF, RealNVP, NICE
09.Priors For Infinite Networks (1994)
Paper Review by Seunghan Lee
(TFP) 10.Bijectors for NF
Bijectors for NF
08.Probabilistic Backpropagation for Scalable Learning of Bayesian Neural Networks(2015)
Paper Review by Seunghan Lee
(TFP) 09.Tensorflow Probability 기본 (3)
Dense Variational Layer, Epistemic + Aleatoric uncertainty
07.Expecation Propagation for Approximate Bayesian Inference(2001)
Paper Review by Seunghan Lee
(TFP) 08.Tensorflow Probability 기본 (2)
Distribution Lambda Layer,Probabilistic Layer
06.Weight Uncertainty in Neural Networks(2015)
Paper Review by Seunghan Lee
(TFP) 07.Tensorflow Probability 기본 (1)
Distribution, Covariance, Independent, Trainable Distribution
05.Ensemble Learning in Bayesian Neural Networks(1998)
Paper Review by Seunghan Lee
(Pytorch) 06.Variational Auto Encoder
Auto Encoding Variational Bayes (2014)
04.Practical Variational Inference for Neural Networks(2011)
Paper Review by Seunghan Lee
(Pytorch) 05.Monte Carlo Drop Out (MCDO)
paper;Dropout as a Bayesian Approximation ; Representing Model Uncertainty in Deep Learning (2016)
03.Keeping Neural Networks Simple by Minimizing the Description Length of the Weights(1993)
Paper Review by Seunghan Lee
(Pytorch) 04.Deep Ensembles
paper;Simple and Scalable Predictive Uncertainty Estimation using Deep Ensembles(2017)
02-3.Bayesian Learning For Neural Network(1995)
Paper Review by Seunghan Lee
(Pytorch) 03.Bayes by Backprop
paper;Weight Uncertainty in Neural Networks(2015)
02-2.Bayesian Learning For Neural Network(1995)
Paper Review by Seunghan Lee
(Pytorch) 02.Variational Inference
Variational Inference
(PAPER REVIEW) VI/BNN/NF paper 41~50
Variational Inference, Bayesian Neural Network, Normalizing Flows
02-1.Bayesian Learning For Neural Network(1995)
Paper Review by Seunghan Lee
(Pytorch) 01.Adversarial Auto Encoder
paper;Adversarial Autoencoder(2016)
(PAPER REVIEW) VI/BNN/NF paper 31~40
Variational Inference, Bayesian Neural Network, Normalizing Flows
01.A Practical Bayesian Framework for Backpropagation Networks(1992)
Paper Review by Seunghan Lee
(PAPER REVIEW) VI/BNN/NF paper 21~30
Variational Inference, Bayesian Neural Network, Normalizing Flows
(PAPER REVIEW) VI/BNN/NF paper 11~20
Variational Inference, Bayesian Neural Network, Normalizing Flows
(PAPER REVIEW) VI/BNN/NF paper 1~10
Variational Inference, Bayesian Neural Network, Normalizing Flows
Paper list of VI,BNN,NF
Variational Inference, Bayesian Neural Network, Normalizing Flows