Realistic Controlled Time Series Generation with Variational Autoencoder

🧑🏻‍💻 Multivariate Time Series Modelling with Neural SDE driven by Jump Diffusion

TRGAN: A Time-Dependent Generative Adversarial Network for Synthetic Transactional Data Generation

Large Multi-Language Models for News Translation

Python wrapper for TA-Lib (http://ta-lib.org/).

A Collection of Variational Autoencoders (VAE) in PyTorch.

Code, data, and pre-trained models for the paper "Continuous Latent Process Flows" (NeurIPS 2021)

PyTorch code of "Modeling Continuous Stochastic Processes with Dynamic Normalizing Flows" (NeurIPS 2020)

Differentiable SDE solvers with GPU support and efficient sensitivity analysis.

Collection of generative models in Tensorflow

Source code of paper "Differentially Private Generative Adversarial Network"

Synthetic financial time series generation with regime clustering

📈Synthetic financial time series generation with regime clustering📈

[ICML 2023] The official implementation of the paper "TabDDPM: Modelling Tabular Data with Diffusion Models"

PyTorch implementation for OCT-GAN Neural ODE-based Conditional Tabular GANs (WWW 2021)

Gated Recurrent Unit with a Decay mechanism for Multivariate Time Series with Missing Values

Differentiable ODE solvers with full GPU support and O(1)-memory backpropagation.

Code for "Neural Controlled Differential Equations for Irregular Time Series" (Neurips 2020 Spotlight)

Curated notebooks on how to train neural networks using differential privacy and federated learning.

Sequence modeling benchmarks and temporal convolutional networks

Implementation of 2019 Quant GANs: Deep Generation of Financial Time Series paper

ruptures: change point detection in Python

Thesis project done on Generation Financial Time-Series with GANs. The project was a collaboration between Wholesale Banking Advanced Analytics team with ING and University Maastricht.

Variational Recurrent Autoencoder for timeseries clustering in pytorch