Causal Inference with Treatment Measurement Error: A Nonparametric Instrumental Variable Approach

no code implementations • 18 Jun 2022 • Yuchen Zhu, Limor Gultchin, Arthur Gretton, Matt Kusner, Ricardo Silva

We propose a kernel-based nonparametric estimator for the causal effect when the cause is corrupted by error.

Causal Inference

Evaluating Self-Supervised Learning for Molecular Graph Embeddings

no code implementations • 16 Jun 2022 • Hanchen Wang, Jean Kaddour, Shengchao Liu, Jian Tang, Matt Kusner, Joan Lasenby, Qi Liu

Graph Self-Supervised Learning (GSSL) paves the way for learning graph embeddings without expert annotation, which is particularly impactful for molecular graphs since the number of possible molecules is enormous and labels are expensive to obtain.

Benchmarking Management +1

Stochastic Causal Programming for Bounding Treatment Effects

1 code implementation • 22 Feb 2022 • Kirtan Padh, Jakob Zeitler, David Watson, Matt Kusner, Ricardo Silva, Niki Kilbertus

Causal effect estimation is important for many tasks in the natural and social sciences.

Counterfactual Data Augmentation for Neural Machine Translation

1 code implementation • NAACL 2021 • Qi Liu, Matt Kusner, Phil Blunsom

We propose a data augmentation method for neural machine translation.

Data Augmentation Language Modelling +2

Pre-Training by Completing Point Clouds

no code implementations • 28 Sep 2020 • Hanchen Wang, Qi Liu, Xiangyu Yue, Joan Lasenby, Matt Kusner

There has recently been a flurry of exciting advances in deep learning models on point clouds.

Learning Binary Trees via Sparse Relaxation

no code implementations • 28 Sep 2020 • Valentina Zantedeschi, Matt Kusner, Vlad Niculae

In this work we derive a novel sparse relaxation for binary tree learning.

regression