Estimating categorical counterfactuals via deep twin networks

نویسندگان

چکیده

Counterfactual inference is a powerful tool, capable of solving challenging problems in high-profile sectors. To perform counterfactual inference, we require knowledge the underlying causal mechanisms. However, mechanisms cannot be uniquely determined from observations and interventions alone. This raises question how to choose so that resulting trustworthy given domain. has been addressed models with binary variables, but for case categorical it remains unanswered. We address this challenge by introducing variables notion ordering, principle positing desirable properties should possess prove equivalent specific functional constraints on learn satisfying these constraints, them, introduce deep twin networks. These are neural networks that, when trained, network inference—an alternative abduction–action–prediction method. empirically test our approach diverse real-world semisynthetic data medicine, epidemiology finance, reporting accurate estimation probabilities while demonstrating issues arise reasoning ordering not enforced When learning model data, deriving examples can help evaluate plausible create hypotheses tested new data. Vlontzos colleagues develop learning-based method answering queries deal rather than only ones, using ‘counterfactual ordering’.

برای دانلود رایگان متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

منابع مشابه

Estimating Cartesian Compression via Deep Learning

We introduce a learning architecture that can serve compression while it also satisfies the constraints of factored reinforcement learning. Our novel Cartesian factors enable one to decrease the number of variables being relevant for the ongoing task, an exponential gain in the size of the state space. We demonstrate the working, the limitations and the promises of the abstractions: we develop ...

متن کامل

Agent Morality via Counterfactuals in Logic Programming

This paper presents a computational model, via Logic Programming (LP), of counterfactual reasoning with applications to agent morality. Counterfactuals are conjectures about what would have happened, had an alternative event occurred. In the first part, we show how counterfactual reasoning, inspired by Pearl’s structural causal model of counterfactuals, is modeled using LP, by benefiting from L...

متن کامل

Choice by Elimination via Deep Neural Networks

We introduce Neural Choice by Elimination, a new framework that integrates deep neural networks into probabilistic sequential choice models for learning to rank. Given a set of items to chose from, the elimination strategy starts with the whole item set and iteratively eliminates the least worthy item in the remaining subset. We prove that the choice by elimination is equivalent to marginalizin...

متن کامل

Reactive Ground Vehicle Control via Deep Networks

We present a deep learning based reactive controller that uses a simple network architecture requiring few training images. Despite its simple structure and small size, our network architecture, called ControlNet, outperforms more complex networks in multiple environments using different robot platforms. We evaluate ControlNet in structured indoor environments and unstructured outdoor environme...

متن کامل

Collaborative Deep Embedding via Dual Networks

Despite the long history of research on recommender systems, current approaches still face a number of challenges in practice, e.g. the difficulties in handling new items, the high diversity of user interests, and the noisiness and sparsity of observations. Many of such difficulties stem from the lack of expressive power to capture the complex relations between items and users. This paper prese...

متن کامل

ذخیره در منابع من


  با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید

ژورنال

عنوان ژورنال: Nature Machine Intelligence

سال: 2023

ISSN: ['2522-5839']

DOI: https://doi.org/10.1038/s42256-023-00611-x