PyTorch code and models for V-JEPA self-supervised learning from video.

(ICML2020) “Counterfactual Cross-Validation: Stable Model Selection Procedure for Causal Inference Models’’

Working repository for Causal Tree and extensions

Construct orhogonal polynomials using Python

Introduction to Uncertainty Quantification

ELECTRA: Pre-training Text Encoders as Discriminators Rather Than Generators

Neural reparameterization improves structural optimization

DeepSurv is a deep learning approach to survival analysis.

Python implementation of the paper "Discrete Differential-Geometry Operators for Triangulated 2-Manifolds" by Meyer et. al. VisMath 2002

Code for the paper "A Deep Reinforced Sequence-to-Set Model for Multi-Label Classification"

Sequence Generation Model for Multi-label Classification (COLING 2018)

This repository provides the code used to implement the framework to provide deep learning models with total uncertainty estimates as described in "A General Framework for Uncertainty Estimation in…

Mixed Incremental Cross-Entropy REINFORCE ICLR 2016

Deep Reinforcement Learning For Sequence to Sequence Models

Experimentation for oracle based contextual bandit algorithms.

LP-SparseMAP: Differentiable sparse structured prediction in coarse factor graphs

This project contains code for paper Ksenia Konyushkova, Raphael Sznitman, Pascal Fua 'Learning Active Learning from Data', NIPS 2017

Torch modules that wrap blackbox combinatorial solvers according to the method presented in "Differentiating Blackbox Combinatorial Solvers"

A platform for Reasoning systems (Reinforcement Learning, Contextual Bandits, etc.)

Simple and easily configurable grid world environments for reinforcement learning

A simple implementation of domain adversarial training with GAN loss in Keras

DoWhy is a Python library for causal inference that supports explicit modeling and testing of causal assumptions. DoWhy is based on a unified language for causal inference, combining causal graphic…

ALICE (Automated Learning and Intelligence for Causation and Economics) is a Microsoft Research project aimed at applying Artificial Intelligence concepts to economic decision making. One of its go…

Causal Effect Inference with Deep Latent-Variable Models