Popular GitHub Repositories for Marginal Likelihood

[CVPR 2022 Oral] Marginal Correspondence for Conditional Image Generation, [CVPR 2021] Unbalanced Feature Transport for Exemplar-based Image Translation

Official repository of CVPRW2022 paper, ElasticFace: Elastic Margin Loss for Deep Face Recognition

Official code for "Maximum Likelihood Training of Score-Based Diffusion Models", NeurIPS 2021 (spotlight)

Likelihood-free AMortized Posterior Estimation with PyTorch

Probabilistic Machine Learning for Finance and Investing: A Primer to Generative AI with Python

Deep Kernel Learning. Gaussian Process Regression where the input is a neural network mapping of x that maximizes the marginal likelihood

Official PyTorch implementation of Harmonizing Maximum Likelihood with GANs for Multimodal Conditional Generation (ICLR 2019)

The official implementation of DiffAbXL benchmarked in the paper "Exploring Log-Likelihood Scores for Ranking Antibody Sequence Designs", formerly titled "Benchmarking Generative Models for Antibody Design".

Density estimation likelihood-free inference. No longer actively developed see https://github.com/mackelab/sbi instead

Roundtrip: density estimation with deep generative neural networks

PyTorch code for FLD (Feature Likelihood Divergence), FID, KID, Precision, Recall, etc. using DINOv2, InceptionV3, CLIP, etc.

Inverse Reinforcement Learning via State Marginal Matching, CoRL 2020

Perform a survival analysis based on the time-to-event (death event) for the subjects. Compare machine learning models to assess the likelihood of a death by heart failure condition. This can be used to help hospitals in assessing the severity of patients with cardiovascular diseases and heart failure condition.

Predicting the likelihood of what the driver is doing in each of the pictures in the dataset.

Python+Rust implementation of the Probabilistic Principal Component Analysis model

Optimizing Physics-Informed NN using Multi-task Likelihood Loss Balance Algorithm and Adaptive Activation Function Algorithm

Adaptive evaluation reveals that most examined adversarial defenses for GNNs show no or only marginal improvement in robustness. (NeurIPS 2022)

A pip library for calculating the Shapley Value for computing the marginal contribution of each client in a Federated Learning environment.

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).

Generative model based HMM model