rpatrik96 / ima-vae
This is the code for the paper Embrace the Gap: VAEs perform Independent Mechanism Analysis, showing that optimizing the ELBO is equivalent to optimizing the IMA-regularized log-likelihood under certain assumptions (e.g., small decoder variance).
☆22Updated 4 months ago
Related projects: ⓘ
- ☆21Updated 9 months ago
- Random feature latent variable models in Python☆21Updated last year
- ☆34Updated last month
- A set of tests for evaluating large-scale algorithms for Wasserstein-1 transport computation (NeurIPS'22).☆19Updated last week
- Code for the paper: "Independent mechanism analysis, a new concept?"☆25Updated last year
- Code for the paper "Disentanglement by Nonlinear ICA with General Incompressible-flow Networks (GIN)" (2020)☆31Updated 2 years ago
- Code accompanying paper: Meta-Learning to Improve Pre-Training☆36Updated 2 years ago
- ☆16Updated 8 months ago
- VAEs and nonlinear ICA: a unifying framework☆27Updated 4 years ago
- Implementation of the models and datasets used in "An Information-theoretic Approach to Distribution Shifts"☆24Updated 2 years ago
- PyTorch implementation of the paper "Continuous Wasserstein-2 Barycenter Estimation without Minimax Optimization" (ICLR 2021)☆21Updated 2 years ago
- Experiments to reproduce results in Interventional Causal Representation Learning.☆25Updated last year
- ☆17Updated 2 years ago
- ☆19Updated 4 years ago
- Code to reproduce the experimental results from the paper "Active Invariant Causal Prediction: Experiment Selection Through Stability", b…☆19Updated last year
- Improving Transformation Invariance in Contrastive Representation Learning☆13Updated 3 years ago
- ☆15Updated last year
- Official repository of the paper "Efficient Neural Causal Discovery without Acyclicity Constraints"☆78Updated 5 months ago
- Euclidean Wasserstein-2 optimal transportation☆43Updated last year
- Code repository of the paper "CITRIS: Causal Identifiability from Temporal Intervened Sequences" and "iCITRIS: Causal Representation Lear…☆47Updated last year
- Code to accompany paper 'Bayesian Deep Ensembles via the Neural Tangent Kernel'☆26Updated 3 years ago
- Code for GFlowNet-EM, a novel algorithm for fitting latent variable models with compositional latents and an intractable true posterior.☆38Updated 7 months ago
- Learning Generative Models across Incomparable Spaces (ICML 2019)☆26Updated 4 years ago
- Python3 implementation of the paper [Large-scale optimal transport map estimation using projection pursuit]☆16Updated 3 years ago
- DynGFN: Bayesian Dynamic Causal Discovery using Generative Flow Networks☆46Updated 6 months ago
- Code for "Causal autoregressive flows" - AISTATS, 2021☆44Updated 3 years ago
- Official code for the ICLR 2021 paper Neural ODE Processes☆71Updated 2 years ago
- Bayesian Attention Modules☆35Updated 3 years ago
- Code for Accelerated Linearized Laplace Approximation for Bayesian Deep Learning (ELLA, NeurIPS 22')☆16Updated last year
- [CLeaR23] Causal Triplet: An Open Challenge for Intervention-centric Causal Representation Learning☆29Updated last year