Lightning Talk: Deep Causal Learning @MicrosoftResearch

Microsoft Research | Lightning Talk: Deep Causal Learning @MicrosoftResearch | Uploaded December 2022 | Updated October 2024, 1 week ago.
Join Microsoft Research at NeurIPS 2022 for the live streaming of presentations and demos from Booth #202.

This year at the 36th annual conference on Neural Information Processing Systems, over 150 of our researchers are involved in presentations, posters, accepted papers, and workshops. Learn more about Microsoft’s presence at NeurIPS 2022: aka.ms/microsoftatneurips2022

---

Nick Pawlowski, Senior Researcher, Microsoft Research Cambridge & Cheng Zhang, Principal Researcher, Microsoft Research Cambridge

Interpretability, Responsibility and Controllability of Human Behaviors

Wildlife Conflict Resolution: Boma & Cattle Detection in the Masai Mara using AI

Research Forum: Closing Remarks and Announcements

Effective Human-AI Decision-Making or Everyone: A Sisyphean Task?

Getting Modular with Language Models: Building, Reusing a Library of Experts for Task Generalization

$Optimization from Structured Samples for Coverage and Influence Functions 2022 Data-driven Optimization Workshop: Optimization from Structured Samples for Coverage and Influence Functions Speaker: Zhijie Zhang, Fuzhou University We revisit the optimization from samples (OPS) model, which studies the problem of optimizing objective functions directly from the sample data. Previous results showed that we cannot obtain a constant approximation ratio for the maximum coverage problem using polynomial independent samples of the form {S_i,f(S_i )}_(i=1)^t (BRS, STOC17), even if coverage functions are (1-ϵ)-PMAC learnable using these samples (BDF+, SODA12). In this work, to circumvent the impossibility result of OPS, we propose a stronger model called optimization from structured samples (OPSS), where the data samples encode the structural information of the functions. We show that under OPSS model, the maximum coverage problem enjoys constant approximation under mild assumptions on the sample distribution. We further generalize the result and show that influence maximization also enjoys constant approximation under this model.$

Evaluation and Understanding of Foundation Models

Fighting the Global Social Media Infodemic: from Fake News to Harmful Content

Final intern talk: Distilling Self-Supervised-Learning-Based Speech Quality Assessment into Compact

AI Forum 2023 | The Emergence of General AI for Medicine