Lecture

Decentralized ML: Collaborative Training & Causal Influence Structure

Description

This lecture covers steps towards collaborative and decentralized machine learning, focusing on communication efficiency, gradient compression, and error feedback for model updates. It also explores building blocks like robustness, privacy, and efficiency. Additionally, it delves into causal influence structure discovery using Bayesian networks, directed information graphs, and beyond single-domain observational setups.

About this result
This page is automatically generated and may contain information that is not correct, complete, up-to-date, or relevant to your search query. The same applies to every other page on this website. Please make sure to verify the information with EPFL's official sources.