| NSF Org: |
IIS Div Of Information & Intelligent Systems |
| Recipient: |
|
| Initial Amendment Date: | July 22, 2019 |
| Latest Amendment Date: | September 14, 2022 |
| Award Number: | 1910077 |
| Award Instrument: | Standard Grant |
| Program Manager: |
Vladimir Pavlovic
vpavlovi@nsf.gov (703)292-8318 IIS Div Of Information & Intelligent Systems CSE Direct For Computer & Info Scie & Enginr |
| Start Date: | October 1, 2019 |
| End Date: | September 30, 2022 (Estimated) |
| Total Intended Award Amount: | $449,735.00 |
| Total Awarded Amount to Date: | $465,735.00 |
| Funds Obligated to Date: |
FY 2020 = $16,000.00 |
| History of Investigator: |
|
| Recipient Sponsored Research Office: |
926 DALNEY ST NW ATLANTA GA US 30318-6395 (404)894-4819 |
| Sponsor Congressional District: |
|
| Primary Place of Performance: |
225 North Avenue Atlanta GA US 30332-0002 |
| Primary Place of
Performance Congressional District: |
|
| Unique Entity Identifier (UEI): |
|
| Parent UEI: |
|
| NSF Program(s): | Robust Intelligence |
| Primary Program Source: |
01002021DB NSF RESEARCH & RELATED ACTIVIT |
| Program Reference Code(s): |
|
| Program Element Code(s): |
|
| Award Agency Code: | 4900 |
| Fund Agency Code: | 4900 |
| Assistance Listing Number(s): | 47.070 |
ABSTRACT
Machine Learning systems are becoming ubiquitous and increasingly complex in modern life. Many devices such as mobile phones continually run dozens of predictive models, and these models receive input not only from the user but also from each other. One way to think about the unexpected challenges of multiple interacting learning systems is to consider how humans interact in personal relationships or even how governments engage with each other during international disputes. Such scenarios involve hard-to-predict dynamics, where the introduction of a small amount of information or minor changes to strategy can give rise to highly different outcomes. This project aims to understand these interacting dynamics from an algorithmic perspective, with an eye towards designing modular learning systems where the implementer can be certain that the dynamics of training will reach a desired solution. The work will significantly increase the range of tasks and challenges where learning systems are applied in the real world and will have a strong impact on how artificial intelligence interacts with society.
The project begins with a focus on game theory and builds off of a number of both classical and recent results in solving so-called min-max problems, where one wants to find the equilibrium of a zero-sum game. The hugely popular Generative Adversarial Networks provide a great example where the training objective is framed as two competing modules engaged in a search for a min-max solution. There has been a great deal of work in finding equilibria using learning systems, and recent work by the investigator has shown that several fundamental convex optimization procedures can be viewed through the lens of learning in repeated play. The award will help support the further development of mathematical frameworks to extend these results beyond convex optimization and to design efficient algorithms with provable guarantees in non-convex settings. One of the areas of particular interest will be the use of continuous-time analysis in training complex multiplayer problems, to understand when such dynamics lead to stable outcomes and when they elicit chaotic behavior.
This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.
PROJECT OUTCOMES REPORT
Disclaimer
This Project Outcomes Report for the General Public is displayed verbatim as submitted by the Principal Investigator (PI) for this award. Any opinions, findings, and conclusions or recommendations expressed in this Report are those of the PI and do not necessarily reflect the views of the National Science Foundation; NSF has not approved or endorsed its content.
As machine learning tools become ubiquitous in society, there is a growing need to understand the dynamics of systems that leverage data in non-centralized ways in order to produce models and procedures that can support us in our daily lives. If these dynamics are not designed carefully, we may waste significant resources on training procedures, or even worse we will end up with non-robust models due to adversarial corruption. This project was able to develop a large number of mostly theoretical tools for understanding these dynamics, and to bring many ideas from convex optimization, economics, and game theory into the world of machine learning. Here is a summary of many of the key ideas we developed over the course of the project:
- A new undrestanding of "accelerating" the progress that players make when playing a game
- New algorithms that leverage this acceleration in novel context, and for interesting and useful environments
- A reframing of many of the algorithms for optimization that are generally not looked at through the lens of game theory.
- Design of new algorithms that are robust to various types of adversarial attack
- A development of new tools that make distributing machine learning computational tasks across a large machines much easier.
We thank the National Science Foundation for their generous support during the course of this award.
Last Modified: 10/17/2023
Modified by: Jacob D Abernethy
Please report errors in award information by writing to: awardsearch@nsf.gov.
