February 4, 2020

174 words 1 min read

On gradient-based methods for finding game-theoretic equilibria

On gradient-based methods for finding game-theoretic equilibria

Statistical decisions are often given meaning in the context of other decisions, particularly when there are scarce resources to be shared. Michael Jordan details the aim to blend gradient-based methodology with game-theoretic goals as part of a large "microeconomics meets machine learning" program.
Talk Title On gradient-based methods for finding game-theoretic equilibria
Speakers Michael Jordan (UC Berkeley)
Conference O’Reilly Artificial Intelligence Conference
Conf Tag Put AI to Work
Location San Jose, California
Date September 10-12, 2019
URL Talk Page
Slides Talk Slides
Video Talk Video

Statistical decisions are often given meaning in the context of other decisions, particularly when there are scarce resources to be shared. The aim is to blend gradient-based methodology with game-theoretic goals as part of a large “microeconomics meets machine learning” program. Michael Jordan details several recent results, including how to define local optimality in nonconvex-nonconcave minimax optimization and how such a definition relates to stochastic gradient methods; a gradient-based algorithm that finds Nash equilibria, and only Nash equilibria; and exploration-exploitation trade-offs for bandits involving competition over a scarce resource.

economics algorithm exploit optimization machine learning
comments powered by Disqus
Best practices for scaling modeling platforms

Best practices for scaling modeling platforms

January 2, 2020

Companies are increasingly building modeling platforms to empower their researchers to efficiently scale the development and productionalization of their models. Scott Clark and Matt Greenwood share a case study from a leading algorithmic trading firm to illustrate best practices for building these types of platforms in any industry.
Deep learning for recommender systems, Or How to compare pears with apples

Deep learning for recommender systems, Or How to compare pears with apples

January 1, 2020

Recommender systems support decision making with personalized suggestions and have proven useful in ecommerce, entertainment, and social networks. Sparse data and linear models are a burden, but the application of deep learning sets new boundaries and offers remarkable results. Join Marcel Kurovski to explore a use case for vehicle recommendations at Germany's biggest online vehicle market.
Deploying data science for national economic statistics

Deploying data science for national economic statistics

December 25, 2019

Jeff Chen shares strategies for overcoming time series challenges at the intersection of macroeconomics and data science, drawing from machine learning research conducted at the Bureau of Economic Analysis aimed at improving its flagship product the gross domestic product.
Large Scale Distributed Deep Learning on Kubernetes Clusters

Large Scale Distributed Deep Learning on Kubernetes Clusters

October 2, 2019

The focus of this talk is the deployments of large scale distributed deep learning with Kubernetes. The usage of operators to manage and automate training processes for machine learning are discussed. …
Open-endedness: A new grand challenge for AI

Open-endedness: A new grand challenge for AI

February 4, 2020

We think a lot in machine learning about encouraging computers to solve problems, but there's another kind of learning, called open-endedness, that's just beginning to attract attention in the field. Kenneth Stanley walks you through how open-ended algorithms keep on inventing new and ever-more complex tasks and solving them continuallyeven endlessly.
Running large-scale machine learning experiments in the cloud

Running large-scale machine learning experiments in the cloud

February 3, 2020

Machine learning involves a lot of experimentation. Data scientists spend days, weeks, or months performing algorithm searches, model architecture searches, hyperparameter searches, etc. Shashank Prasanna breaks down how you can easily run large-scale machine learning experiments using containers, Kubernetes, Amazon ECS, and SageMaker.