Causality and Machine Learning

新闻与深度文章

diagram
文章

Given a language model, can we tell whet…

Research Focus: April 23, 2025
微软研究院博客

In this issue: our CHI 2025 & ICLR 2025 …

What's Your Story podcast | Emre Kiciman
微软研究院播客

| Johannes Gehrke 和 Emre Kiciman

Emre Kiciman shares how some keen observ…

black and white photos of Emre Kiciman, Senior Principal Researcher at Microsoft Research and Amit Sharma, Principal Researcher at Microsoft Reserach, next to the Microsoft Research Podcast
微软研究院播客

| Ashley Llorens, Emre Kiciman, 和 Amit Sharma

Emre Kiciman and Amit Sharma join Ashley…

Microsoft Research Focus 12 edition, week of March 27, 2023
微软研究院博客

Welcome to Research Focus, a series of b…

Microsoft Research - Research Focus 05 Week of November 28th, 2022
微软研究院博客

This special edition of Research Focus h…

新闻报道 | TechRepublic

Causal machine learning with Microsoft’s…

A flowchart showing the DoWhy library process. Input Data and Domain Knowledge are injected into the library, where they go through four steps: Model causal mechanisms; Identify target estimands; Estimate causal effect; and Refute estimate. The process produces the output labelled Causal effect.
微软研究院博客

| Emre Kiciman 和 Amit Sharma

Identifying causal effects is an integra…

Graphical representation of how our adversarial training approach works for solving the instrumental variable problem. The problem is viewed as a zero-sum game between a learner and an adversary. The learner attempts to find models that satisfy all moment constraints and the adversary flags violating moment constraints. Then the learner tries to correct the model to also satisfy the flagged constraint. A good model is learned when the adversary cannot find large violations
微软研究院博客

| Vasilis Syrgkanis

We are going through a new shift in mach…