Lecture

Algorithms to Live By: Optimal Stopping and Logarithmic Regret

Description

This lecture covers the concept of optimal stopping, explore/exploit trade-offs, sorting, caching, scheduling, Bayes' Rule, overfitting, randomness, networking, game theory, and computational kindness. It also delves into the logarithmic regret in bandit solutions, providing insights into randomized clinical trials, ethical considerations, and near-optimal strategies for treatment outcomes.

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.