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).
☆23Updated 11 months ago
Alternatives and similar repositories for ima-vae:
Users that are interested in ima-vae are comparing it to the libraries listed below
- Code for the paper: "Independent mechanism analysis, a new concept?"☆24Updated last year
- ☆25Updated last year
- ☆27Updated 2 weeks ago
- Experiments to reproduce results in Interventional Causal Representation Learning.☆24Updated 2 years ago
- Code for the paper "Disentanglement by Nonlinear ICA with General Incompressible-flow Networks (GIN)" (2020)☆32Updated 3 years ago
- ☆15Updated 2 years ago
- Code for ICE-BeeM paper - NeurIPS 2020☆86Updated 3 years ago
- Code to reproduce the experimental results from the paper "Active Invariant Causal Prediction: Experiment Selection Through Stability", b…☆20Updated last year
- Code accompanying paper: Meta-Learning to Improve Pre-Training☆37Updated 3 years ago
- ☆37Updated 8 months ago
- ☆53Updated 8 months ago
- ☆17Updated last year
- Implementation of the models and datasets used in "An Information-theoretic Approach to Distribution Shifts"☆25Updated 3 years ago
- A set of tests for evaluating large-scale algorithms for Wasserstein-1 transport computation (NeurIPS'22).☆20Updated 7 months ago
- [CLeaR23] Causal Triplet: An Open Challenge for Intervention-centric Causal Representation Learning☆30Updated 2 years ago
- Laplace Redux -- Effortless Bayesian Deep Learning☆43Updated 2 years ago
- Code for GFlowNet-EM, a novel algorithm for fitting latent variable models with compositional latents and an intractable true posterior.☆40Updated last year
- Official repository of the paper "Efficient Neural Causal Discovery without Acyclicity Constraints"☆82Updated last year
- Code repository of the paper "CITRIS: Causal Identifiability from Temporal Intervened Sequences" and "iCITRIS: Causal Representation Lear…☆51Updated last year
- Bayesian Attention Modules☆35Updated 4 years ago
- NeurIPS'23: Energy Discrepancies: A Score-Independent Loss for Energy-Based Models☆16Updated 5 months ago
- ☆29Updated last year
- ☆20Updated 4 years ago
- Self-Supervised Learning with Data Augmentations Provably Isolates Content from Style☆51Updated 3 years ago
- Improving Transformation Invariance in Contrastive Representation Learning☆13Updated 4 years ago
- DynGFN: Bayesian Dynamic Causal Discovery using Generative Flow Networks☆52Updated last year
- Random feature latent variable models in Python☆22Updated last year
- [NeurIPS'20] Code for the Paper Compositional Visual Generation and Inference with Energy Based Models☆44Updated 2 years ago
- Code for "Causal autoregressive flows" - AISTATS, 2021☆44Updated 4 years ago
- Transformers with doubly stochastic attention☆45Updated 2 years ago