Éva Tardos, the Jacob Gould Schurman Professor of Computer Science at Cornell University, is seen standing at a whiteboard with an equation written on it, holding a marker in her hand
Éva Tardos, the Jacob Gould Schurman Professor of Computer Science at Cornell University, is the winner of both the Association for Computer Machinery’s Gödel Prize and the Institute of Electrical and Electronics Engineers’ John von Neumann medal. Her research focuses on algorithmic game theory, or the application of game theory to algorithm design.
Dave Burbank

Learning in game-theoretical models

Amazon Research Award recipient Éva Tardos studies complex theoretical questions that have far-ranging practical consequences.

Game theory is a mathematical way to describe strategic reasoning. In the game-theoretical sense, a game involves players who choose actions and, depending on their choices and those of the other players, receive different levels of reward. Since 2005, the Nobel Prize in economics has gone to game-theoretical work four times.

Éva Tardos, the Jacob Gould Schurman Professor of Computer Science at Cornell University, is the winner of both the Association for Computer Machinery’s Gödel Prize and the Institute of Electrical and Electronics Engineers’ John von Neumann medal (named for the man who created game theory, among other accomplishments). Her research focuses on algorithmic game theory, or the application of game theory to algorithm design.

In 2018, Tardos received an Amazon Research Award to pursue the topic of learning in games: Over repeated iterations of the same game, can the players learn the strategies that will maximize their rewards? And can the game be structured so that the individual players’ reward maximization strategies also maximize the common good?

“The question I’m most fascinated by has three prongs,” Tardos says. “One is, ‘What can we say about the quality of outcomes if people learn?’ Another is, ‘What does it mean to learn?’ When I look at what users did, what conditions of learning do people actually satisfy?

“And third — and maybe that's in some ways the most actionable — is, ‘What is the right form of learning in a changing environment?’ If you’re Amazon, and you want to learn how to price your products, what is your stockpile? How many books do you have? If you're selling them, you're going to have less. There is some carryover effect over time. What does that tell you? What is the right format of learning in cases when there's a changing environment, and there's a carryover effect? And then of course, do people learn in that way?”

Concepts of learning

As an example of a game, consider a penalty kick in soccer, in which the kicker shoots at either the right or left half of the goal, and the goalie guesses which way to dive. In the simplest game-theoretical model of the game, if both goalie and kicker pick the same direction, the goalie wins; if they pick different directions, the kicker wins.

On this model, if both players are trying to maximize their chances of winning, their optimal strategy is to go left or right randomly, with equal probability in either direction. If one player deviates from that strategy, the other player has an opportunity to increase his or her winning percentage.

A set of strategies that no player in a game has an incentive to change unilaterally is called a Nash equilibrium. The penalty-kick game is a zero-sum game: if one player wins, the other loses. But many real-world scenarios — for instance, choosing driving routes during rush hour — can be modeled as non-zero-sum games, and they have Nash equilibria, too.

One early hypothesis about learning in game theory was that, over repeated iterations of a game, players converge toward the Nash equilibrium. But more recent research suggests that that’s unlikely, as Nash equilibria for complex games are intractably hard to compute.

Your learning should be good enough to observe that that's better than what you are doing. And that's called no-regret learning.
Éva Tardos

In many circumstances, Tardos explains, game theorists have settled for a more relaxed standard of learning, called “no-regret learning”, which has the advantage of being algorithmically achievable.

“If there is a single strategy that would have been consistently pretty good over time, then please do at least as well as that one,” Tardos says. “If there is a route on which every day you would get to work pretty damn fast, you don't have to drive that, but if you're doing worse than that, something went wrong. Your learning should be good enough to observe that that's better than what you are doing. And that's called no-regret learning.”

Carryover effects

Much of Tardos’s recent work on learning in game theory has focused on games with carryover effects. What are the best learning algorithms for such games? Under what circumstances can learning occur? And how do the learned strategies compare to the optimal distribution of strategies?

Tardos has investigated these questions in the contexts of two applications in particular: ad auctions, in which advertisers bid for ad space on websites, and packet-switched network routing, of the type we see on the Internet.

In the case of ad auctions, the carryover effect is that a successful bid for an ad reduces the budget that the ad buyer has for additional purchases. Tardos and her colleagues have analyzed real-world data and concluded that, in ad auctions, no-regret learning can occur, but only for ad buyers with adequate resources. Otherwise, budget limitations prevent them from exploring the space of options thoroughly enough to identify good strategies.

Eva Tardos: Games, auctions, learning, and the price of anarchy

In the case of packet-switched routing, the carryover effect is that unsuccessful packet transmission causes senders to resend packets, which increases network congestion. Tardos and her colleagues showed that learning can ensure efficient system performance, but only if each router in the network can handle enough incoming packets simultaneously.

Here, however, Tardos and her colleagues’ analysis was theoretical, so they could compare players’ learned strategies to the optimal strategy if some omniscient planner allocated network bandwidth according senders’ transmission needs. They found that, if senders are simply trying to learn strategies that maximize their own network throughputs, then in order to ensure that everyone’s packets get through, the router capacity needs to be about twice what it would be in the optimal case.

In a follow-up study, however, Tardos and one of her students showed that a better learning algorithm could nudge the players’ learned strategies closer to the optimum. If the players are patient enough — if they adhere to a given transmission strategy long enough to get a reliable signal of its long-term efficacy — then learning will lead to efficient routing with only about 1.6 times the optimal router capacity.

These are preliminary results, but they demonstrate a methodology for making progress on a set of very difficult, interrelated problems. In ongoing work, Tardos is generalizing the same techniques of analysis to the relationships between product pricing and inventory management, in which the carryover effect is the amount of inventory on hand, depending on sales rates at different price points. And that’s a problem of obvious interest to Amazon.

“There are questions that we’re not answering that would be lovely to answer,” Tardos says. “And these are all ongoing projects. So maybe we will answer them eventually.”

Related content

US, CA, San Francisco
About Twitch Launched in 2011, Twitch is a global community that comes together each day to create multiplayer entertainment: unique, live, unpredictable experiences created by the interactions of millions. We bring the joy of co-op to everything, from casual gaming to world-class esports to anime marathons, music, and art streams. Twitch also hosts TwitchCon, where we bring everyone together to celebrate, learn, and grow their personal interests and passions. We’re always live at Twitch. Stay up to date on all things Twitch on Linkedin, Twitter and on our Blog. About the role: Twitch builds data-driven machine learning solutions across several rich problem spaces: Natural Language Processing (NLP), Recommendations, Semantic Search, Classification/Categorization, Anomaly Detection, Forecasting, Safety, and HCI/Social Computing/Computational Social Science. As an Intern, you will work with a dedicated Mentor and Manager on a project in one of these problem areas. You will also be supported by an Advisor and participate in cohort activities such as research teach backs and leadership talks. This position can also be located in San Francisco, CA or virtual. You Will: Solve large-scale data problems. Design solutions for Twitch's problem spaces Explore ML and data research
US, CA, San Francisco
About Twitch Launched in 2011, Twitch is a global community that comes together each day to create multiplayer entertainment: unique, live, unpredictable experiences created by the interactions of millions. We bring the joy of co-op to everything, from casual gaming to world-class esports to anime marathons, music, and art streams. Twitch also hosts TwitchCon, where we bring everyone together to celebrate, learn, and grow their personal interests and passions. We’re always live at Twitch. Stay up to date on all things Twitch on Linkedin, Twitter and on our Blog. About the role: Twitch builds data-driven machine learning solutions across several rich problem spaces: Natural Language Processing (NLP), Recommendations, Semantic Search, Classification/Categorization, Anomaly Detection, Forecasting, Safety, and HCI/Social Computing/Computational Social Science. As an Intern, you will work with a dedicated Mentor and Manager on a project in one of these problem areas. You will also be supported by an Advisor and participate in cohort activities such as research teach backs and leadership talks. This position can also be located in San Francisco, CA or virtual. You Will: Solve large-scale data problems. Design solutions for Twitch's problem spaces Explore ML and data research
LU, Luxembourg
Are you a talented and inventive scientist with a strong passion about modern data technologies and interested to improve business processes, extracting value from the data? Would you like to be a part of an organization that is aiming to use self-learning technology to process data in order to support the management of the procurement function? The Global Procurement Technology, as a part of Global Procurement Operations, is seeking a skilled Data Scientist to help build its future data intelligence in business ecosystem, working with large distributed systems of data and providing Machine Learning (ML) and Predictive Modeling expertise. You will be a member of the Data Engineering and ML Team, joining a fast-growing global organization, with a great vision to transform the Procurement field, and become the role model in the market. This team plays a strategic role supporting the core Procurement business domains as well as it is the cornerstone of any transformation and innovation initiative. Our mission is to provide a high-quality data environment to facilitate process optimization and business digitalization, on a global scale. We are supporting business initiatives, including but not limited to, strategic supplier sourcing (e.g. contracting, negotiation, spend analysis, market research, etc.), order management, supplier performance, etc. We are seeking an individual who can thrive in a fast-paced work environment, be collaborative and share knowledge and experience with his colleagues. You are expected to deliver results, but at the same time have fun with your teammates and enjoy working in the company. In Amazon, you will find all the resources required to learn new skills, grow your career, and become a better professional. You will connect with world leaders in your field and you will be tackling Data Science challenges to ensure business continuity, by taking the right decisions for your customers. As a Data Scientist in the team, you will: -be the subject matter expert to support team strategies that will take Global Procurement Operations towards world-class predictive maintenance practices and processes, driving more effective procurement functions, e.g. supplier segmentation, negotiations, shipping supplies volume forecast, spend management, etc. -have strong analytical skills and excel in the design, creation, management, and enterprise use of large data sets, combining raw data from different sources -provide technical expertise to support the development of ML models to facilitate intelligent digital services, such as Contract Lifecycle Management (CLM) and Negotiations platform -cooperate closely with different groups of stakeholders, e.g. data/software engineers, product/program managers, analysts, senior leadership, etc. to evaluate business needs and objectives to set up the best data management environment -create and share with audiences of varying levels technical papers and presentations -deal with ambiguity, prioritizing needs, and delivering results in a dynamic environment Basic qualifications -Master’s Degree in Computer Science/Engineering, Informatics, Mathematics, or a related technical discipline -3+ years of industry experience in data engineering/science, business intelligence or related field -3+ years experience in algorithm design, engineering and implementation for very-large scale applications to solve real problems -Very good knowledge of data modeling and evaluation -Very good understanding of regression modeling, forecasting techniques, time series analysis, machine-learning concepts such as supervised and unsupervised learning, classification, random forest, etc. -SQL and query performance tuning skills Preferred qualifications -2+ years of proficiency in using R, Python, Scala, Java or any modern language for data processing and statistical analysis -Experience with various RDBMS, such as PostgreSQL, MS SQL Server, MySQL, etc. -Experience architecting Big Data and ML solutions with AWS products (Redshift, DynamoDB, Lambda, S3, EMR, SageMaker, Lex, Kendra, Forecast etc.) -Experience articulating business questions and using quantitative techniques to arrive at a solution using available data -Experience with agile/scrum methodologies and its benefits of managing projects efficiently and delivering results iteratively -Excellent written and verbal communication skills including data visualization, especially in regards to quantitative topics discussed with non-technical colleagues
US, CA, San Francisco
About Twitch Launched in 2011, Twitch is a global community that comes together each day to create multiplayer entertainment: unique, live, unpredictable experiences created by the interactions of millions. We bring the joy of co-op to everything, from casual gaming to world-class esports to anime marathons, music, and art streams. Twitch also hosts TwitchCon, where we bring everyone together to celebrate, learn, and grow their personal interests and passions. We’re always live at Twitch. Stay up to date on all things Twitch on Linkedin, Twitter and on our Blog. About the role: Twitch builds data-driven machine learning solutions across several rich problem spaces: Natural Language Processing (NLP), Recommendations, Semantic Search, Classification/Categorization, Anomaly Detection, Forecasting, Safety, and HCI/Social Computing/Computational Social Science. As an Intern, you will work with a dedicated Mentor and Manager on a project in one of these problem areas. You will also be supported by an Advisor and participate in cohort activities such as research teach backs and leadership talks. This position can also be located in San Francisco, CA or virtual. You Will: Solve large-scale data problems. Design solutions for Twitch's problem spaces Explore ML and data research
US, CA, San Francisco
About Twitch Launched in 2011, Twitch is a global community that comes together each day to create multiplayer entertainment: unique, live, unpredictable experiences created by the interactions of millions. We bring the joy of co-op to everything, from casual gaming to world-class esports to anime marathons, music, and art streams. Twitch also hosts TwitchCon, where we bring everyone together to celebrate, learn, and grow their personal interests and passions. We’re always live at Twitch. Stay up to date on all things Twitch on Linkedin, Twitter and on our Blog. About the role: Twitch builds data-driven machine learning solutions across several rich problem spaces: Natural Language Processing (NLP), Recommendations, Semantic Search, Classification/Categorization, Anomaly Detection, Forecasting, Safety, and HCI/Social Computing/Computational Social Science. As an Intern, you will work with a dedicated Mentor and Manager on a project in one of these problem areas. You will also be supported by an Advisor and participate in cohort activities such as research teach backs and leadership talks. This position can also be located in San Francisco, CA or virtual. You Will: Solve large-scale data problems. Design solutions for Twitch's problem spaces Explore ML and data research
US, CA, San Francisco
About Twitch Launched in 2011, Twitch is a global community that comes together each day to create multiplayer entertainment: unique, live, unpredictable experiences created by the interactions of millions. We bring the joy of co-op to everything, from casual gaming to world-class esports to anime marathons, music, and art streams. Twitch also hosts TwitchCon, where we bring everyone together to celebrate, learn, and grow their personal interests and passions. We’re always live at Twitch. Stay up to date on all things Twitch on Linkedin, Twitter and on our Blog. About the role: Twitch builds data-driven machine learning solutions across several rich problem spaces: Natural Language Processing (NLP), Recommendations, Semantic Search, Classification/Categorization, Anomaly Detection, Forecasting, Safety, and HCI/Social Computing/Computational Social Science. As an Intern, you will work with a dedicated Mentor and Manager on a project in one of these problem areas. You will also be supported by an Advisor and participate in cohort activities such as research teach backs and leadership talks. This position can also be located in San Francisco, CA or virtual. You Will: Solve large-scale data problems. Design solutions for Twitch's problem spaces Explore ML and data research
US, CA, San Francisco
About Twitch Launched in 2011, Twitch is a global community that comes together each day to create multiplayer entertainment: unique, live, unpredictable experiences created by the interactions of millions. We bring the joy of co-op to everything, from casual gaming to world-class esports to anime marathons, music, and art streams. Twitch also hosts TwitchCon, where we bring everyone together to celebrate, learn, and grow their personal interests and passions. We’re always live at Twitch. Stay up to date on all things Twitch on Linkedin, Twitter and on our Blog. About the role: Twitch builds data-driven machine learning solutions across several rich problem spaces: Natural Language Processing (NLP), Recommendations, Semantic Search, Classification/Categorization, Anomaly Detection, Forecasting, Safety, and HCI/Social Computing/Computational Social Science. As an Intern, you will work with a dedicated Mentor and Manager on a project in one of these problem areas. You will also be supported by an Advisor and participate in cohort activities such as research teach backs and leadership talks. This position can also be located in San Francisco, CA or virtual. You Will: Solve large-scale data problems. Design solutions for Twitch's problem spaces Explore ML and data research
US, WA, Seattle
We are a team of doers working passionately to apply cutting-edge advances in deep learning in the life sciences to solve real-world problems. As a Senior Applied Science Manager you will participate in developing exciting products for customers. Our team rewards curiosity while maintaining a laser-focus in bringing products to market. Competitive candidates are responsive, flexible, and able to succeed within an open, collaborative, entrepreneurial, startup-like environment. At the leading edge of both academic and applied research in this product area, you have the opportunity to work together with a diverse and talented team of scientists, engineers, and product managers and collaborate with others teams. Location is in Seattle, US Embrace Diversity Here at Amazon, we embrace our differences. We are committed to furthering our culture of inclusion. We have ten employee-led affinity groups, reaching 40,000 employees in over 190 chapters globally. We have innovative benefit offerings, and host annual and ongoing learning experiences, including our Conversations on Race and Ethnicity (CORE) and AmazeCon (gender diversity) conferences. Amazon’s culture of inclusion is reinforced within our 14 Leadership Principles, which remind team members to seek diverse perspectives, learn and be curious, and earn trust Balance Work and Life Our team puts a high value on work-life balance. It isn’t about how many hours you spend at home or at work; it’s about the flow you establish that brings energy to both parts of your life. We believe striking the right balance between your personal and professional life is critical to life-long happiness and fulfillment. We offer flexibility in working hours and encourage you to find your own balance between your work and personal lives Mentor & Grow Careers Our team is dedicated to supporting new members. We have a broad mix of experience levels and tenures, and we’re building an environment that celebrates knowledge sharing and mentorship. Our senior members enjoy one-on-one mentoring and thorough, but kind, code reviews. We care about your career growth and strive to assign projects based on what will help each team member develop into a better-rounded engineer and enable them to take on more complex tasks in the future. Key job responsibilities • Manage high performing engineering and science teams • Hire and develop top-performing engineers, scientists, and other managers • Develop and execute on project plans and delivery commitments • Work with business, data science, software engineer, biological, and product leaders to help define product requirements and with managers, scientists, and engineers to execute on them • Build and maintain world-class customer experience and operational excellence for your deliverables
US, Virtual
The Amazon Economics Team is hiring Interns in Economics. We are looking for detail-oriented, organized, and responsible individuals who are eager to learn how to work with large and complicated data sets. Some knowledge of econometrics, as well as basic familiarity with Stata, R, or Python is necessary. Experience with SQL, UNIX, Sawtooth, and Spark would be a plus. These are full-time positions at 40 hours per week, with compensation being awarded on an hourly basis. You will learn how to build data sets and perform applied econometric analysis at Internet speed collaborating with economists, data scientists and MBAʼs. These skills will translate well into writing applied chapters in your dissertation and provide you with work experience that may help you with placement. Roughly 85% of interns from previous cohorts have converted to full time economics employment at Amazon. If you are interested, please send your CV to our mailing list at econ-internship@amazon.com.
US, WA, Seattle
Amazon internships are full-time (40 hours/week) for 12 consecutive weeks with start dates in May - July 2023. Our internship program provides hands-on learning and building experiences for students who are interested in a career in hardware engineering. This role will be based in Seattle, and candidates must be willing to work in-person. Corporate Projects (CPT) is a team that sits within the broader Corporate Development organization at Amazon. We seek to bring net-new, strategic projects to life by working together with customers and evolving projects from ZERO-to-ONE. To do so, we deploy our resources towards proofs-of-concept (POCs) and pilot programs and develop them from high-level ideas (the ZERO) to tangible short-term results that provide validating signal and a path to scale (the ONE). We work with our customers to develop and create net-new opportunities by relentlessly scouring all of Amazon and finding new and innovative ways to strengthen and/or accelerate the Amazon Flywheel. CPT seeks an Applied Science intern to work with a diverse, cross-functional team to build new, innovative customer experiences. Within CPT, you will apply both traditional and novel scientific approaches to solve and scale problems and solutions. We are a team where science meets application. A successful candidate will be a self-starter comfortable with ambiguity, strong attention to detail, and the ability to work in a fast-paced, ever-changing environment. As an Applied Science Intern, you will own the design and development of end-to-end systems. You’ll have the opportunity to create technical roadmaps, and drive production level projects that will support Amazon Science. You will work closely with Amazon scientists, and other science interns to develop solutions and deploy them into production. The ideal scientist must have the ability to work with diverse groups of people and cross-functional teams to solve complex business problems.