| 
  • If you are citizen of an European Union member nation, you may not use this service unless you are at least 16 years old.

  • You already know Dokkio is an AI-powered assistant to organize & manage your digital files & messages. Very soon, Dokkio will support Outlook as well as One Drive. Check it out today!

View
 

Markets Mechanisms and Multi-Agent Models

Page history last edited by Amos Storkey 11 years, 4 months ago

 

Markets, Mechanisms, and Multi-Agent Models

Examining the Interaction of Machine Learning and Economics

 


The Complete Papers and Videos for this workshop are available on the archive site:

 

http://workshops.inf.ed.ac.uk/ICML-Markets/

 

Location:

Edinburgh, Scotland, at the ICML 2012 Workshops, IF G07a

 

Date: 

1 July 2012

 

Organisers: 

Amos Storkey

Jacob Abernethy

Jenn Wortman Vaughan

 

Overview:

 

Many of society’s greatest accomplishments are in large part due to the facility of markets. Markets and other allocation mechanisms have become necessary tools of the modern age, and they have been key to facilitating the development of complex structures, advanced engineering, and a range of other improvements to our collective capabilities. Much work in economics has been done to demonstrate that markets can, in aggregate, function very well even when the individual participants are noisy, irrational or myopic.

 

In terms of aims and benefits, the design of machine learning techniques has much in common with the development of market mechanisms: information aggregation, maximal efficiency, scalability, and, more recently, decentralization. Current machine learning algorithms are often single goal methods, built from simple homogeneous units by one person or individual groups. Perhaps looking to the organisations of economies may help in moving beyond the current centralised design of most machine learning methods. Allowing agents with different opinions, approaches or methods to enter and leave the market, to interact, and to adapt to changes can have many benefits. For example it may enable us to develop methods that provide continuous improvement on complex problems, reuse results by improving on previous outcomes rather than building bigger models from scratch, and adapting to changes.

 

There are many relationships between machine learning methods, Bayesian decision theory, risk minimisation, economics, statistical physics and information theory that have been known for some time. There are also many open questions regarding the full nature and impact of these connections. This workshop will explore these connections from many different directions. Some example topics are given below.

 

 

 

Programme:

 

We have organized the following programme for the workshop. The Call for Submissions is still available for viewing.

 

9.00-9.20 Introduction, Amos Storkey: "Markets, Mechanisms and Multi-agent Models"
9.20-10:00 Invited Speaker, Adrian Barbu: "The Artificial Prediction Market"
10:00-10:30 Rafael M. Frongillo, Nicolas Della Penna, Mark D. Reid: "Interpreting prediction markets: a stochastic approach" (PAPER)
10:30-11:00 Coffee Break
11:00-11:30 Moshe Babaioff, Shaddin Dughmi, Robert Kleinberg, Aleksandrs Slivkins: "Dynamic Pricing with Limited Supply"  (PAPER)
11:30-12:00 Amy Greenwald, Jiacui Li, Eric Sodomka: "Approximating Equilibria in Sequential Auctions with Incomplete Information and Multi-Unit Demand" (PAPER)
12:00-12:30 Jan-Peter Calliess, Michael A. Osborne, Stephen Roberts: "Towards auction-based multi-agent collision-avoidance under continuous stochastic dynamics" (PAPER)
12:30-14:00 Lunch
14:00-14:20 Interim Summary and Discussion
14:20-15:00 Invited Speaker, Sebastien Lahaie: "A Tractable Combinatorial Market Maker using Constraint Generation"
15:00-15:30 Xiaolong Li, Jennifer Wortman Vaughan: "Designing Duality-Based Market Makers with Adaptive Liquidity"(PAPER)
15:30-16:00 Coffee and discussion
16:00-16:30 Amir Sani, Alessandro Lazaric, Remi Munos: "Risk–Aversion in Multi–armed Bandits" (PAPER)
16:30-17:00 Maria-Florina Balcan, Florin Constantin, Ruta Mehta: "The Weighted Majority Algorithm does not Converge in Nearly Zero-sum Games" (PAPER)
17:00-17:30 Discussion and Conclusion

 

 

Sponsors:

 

This workshop is sponsored by Microsoft Research, Cambridge

 

 

Comments (0)

You don't have permission to comment on this page.