CausalFlow: a Unified Framework for Causality in Time-Series

📚 A collection of awesome Causality in ST data papers.

The CausalPlayground library serves as a tool for causality research, focusing on the interactive exploration of structural causal models (SCMs). It provides extensive functionality for creating, m…

Joint Diffusion Kalman Filter and Stress Testing Backtests

Multi-Objective Causal Bayesian Optimisation, a new paradigm for finding Pareto-optimal interventions in multi-outcome causal models

Implementation of Deep IV: A Flexible Approach for Counterfactual Prediction

linax is a light weight collection of state space models implemented in JAX ⚡️

Code to run submissions for the Atlantic Causal Inference Competition

The CausalRivers benchmark package. Evaluate your Causal Discovery method on real-world data.

Inference of relative ability from winning probabilities

Agentics is a Python framework that provides structured, scalable, and semantically grounded agentic computation.

Gradient gating (ICLR 2023)

Database for AI. Store Vectors, Images, Texts, Videos, etc. Use with LLMs/LangChain. Store, query, version, & visualize any AI data. Stream data in real-time to PyTorch/TensorFlow. https://activelo…

A high-performance Python-based I/O system for large (and small) deep learning problems, with strong support for PyTorch.

Message-Passing Monte Carlo (MPMC)

Graph similarity learning method for detecting change-points in dynamic networks

Reproducible code for "Causal Change Point Detection and Localization"

Winner-takes-all for Multivariate Probabilistic Time Series Forecasting

This repository implements a Diffusion Factor Model for financial data.

A companion for the Causal Artificial Intelligence book.

Python toolbox for sampling Determinantal Point Processes

A PyTorch implementation of NeRF (Neural Radiance Fields) that reproduces the results.

Data from the M-competitions

Library for graphical models of decision making, based on pgmpy and networkx

Code for "Deep Signature Transforms" (NeurIPS 2019)

Code to accompany the paper "Fin-GAN: Forecasting and Classifying Financial Time Series via Generative Adversarial Networks"

This is the official repository for the paper TLOB: A Novel Transformer Model with Dual Attention for Stock Price Trend Prediction with Limit Order Book Data.

A graph neural network tailored to directed acyclic graphs that outperforms conventional GNNs by leveraging the partial order as strong inductive bias besides other suitable architectural features.

D-VAE: A Variational Autoencoder for Directed Acyclic Graphs, NeurIPS 2019