Stars
Time-series Generative Adversarial Networks (fork from the ML-AIM research group on bitbucket))
Financial pipeline for the data-driven investor to research, develop and deploy robust strategies. Big Data ingestion, risk factor modeling, stock screening, portfolio optimization, and broker API.
Code for ICML 2020 paper: "Time Series Deconfounder: Estimating Treatment Effects over Time in the Presence of Hidden Confounders" by I. Bica, A. M. Alaa, M. van der Schaar
Software relating to relational empirical risk minimization
Library of deep learning models and datasets designed to make deep learning more accessible and accelerate ML research.
A natural language modeling framework based on PyTorch
An open source framework for seq2seq models in PyTorch.
Enhancing the Locality and Breaking the Memory Bottleneck of Transformer on Time Series Forecasting (NeurIPS 2019)
A collection of extensions and data-loaders for few-shot learning & meta-learning in PyTorch
Meta-SGD experiment on Omniglot classification compared with MAML
Repository for the Tetrad Project, www.phil.cmu.edu/tetrad.
DAGs with NO TEARS: Continuous Optimization for Structure Learning
A unified framework for machine learning with time series
JavaScript image gallery for mobile and desktop, modular, framework independent
TIme series DiscoverY BENCHmark (tidybench)
Cf. TIme series DiscoverY BENCHmark (tidybench) https://github.com/sweichwald/tidybench
Package for causal inference in graphs and in the pairwise settings. Tools for graph structure recovery and dependencies are included.
Code for generating Higher-order Network (HON) from data with higher-order dependencies
Algorithms for detection of outliers based on frequent pattern mining
A C++ library for vine copula models (w/ interfaces to R + Python)
Tools to construct canonical and regular vines. StarVine can also be used as a bivariate copula fitting tool.
Optimized Dynamic Programming (Dynamic Time Warp) as a Python external