Course Detail (Course Description By Faculty)

Online Learning, Operations, and Electronic Markets (36922)

Algorithms for sequential decision-making are crucial in the operations of modern online platforms and web-based marketplaces. These algorithms should be designed to make better decisions as more information is revealed over time. The central theme of this course will be studying various families of these algorithms for online learning and prediction, and their applications to game theory and the design of electronic markets and platforms. The emphasis will be on mathematical techniques for designing, analyzing, and applying these algorithms. These mathematical techniques will include algorithms for predicting from expert advice, learning in games (including adaptive game playing, Nash equilibrium, and correlated equilibrium), stochastic and adversarial multi-armed bandit problems, contextual bandits and search, adversarial corruptions, incentivizing exploration, and Markov decision processes/reinforcement learning. We will learn these techniques through the lens of their applications to pricing and auction theory, automatic bidding, recommendation systems, calibrations in forecast, and design of clinical trials/experiments. The topic of each lecture is based on one particular application domain.

 

 

This is a PhD-level course for students with strong quantitative and mathematical backgrounds. The course doesn't have an official prerequisite, but (i) basic graduate-level probability and game theory classes as prerequisites are recommended, and (ii) familiarity with learning theory and convex optimization (at the level of BUSN 36920/36931BUSN 36919, and/or similar courses at TTIC) will be helpful. Students should be comfortable with probability theory, continuous and discrete optimization, and basic algorithms. PhD students only (strict). 

 

  • PhD - students only
  • No pass/fail grades
Description and/or course criteria last updated: June 05 2024
SCHEDULE
  • Spring 2025
    Section: 36922-50
    Day/Time: TBD
    Building: TBD
    Location: TBD
    In-Person Only

Online Learning, Operations, and Electronic Markets (36922) - Niazadeh, Rad>>

Algorithms for sequential decision-making are crucial in the operations of modern online platforms and web-based marketplaces. These algorithms should be designed to make better decisions as more information is revealed over time. The central theme of this course will be studying various families of these algorithms for online learning and prediction, and their applications to game theory and the design of electronic markets and platforms. The emphasis will be on mathematical techniques for designing, analyzing, and applying these algorithms. These mathematical techniques will include algorithms for predicting from expert advice, learning in games (including adaptive game playing, Nash equilibrium, and correlated equilibrium), stochastic and adversarial multi-armed bandit problems, contextual bandits and search, adversarial corruptions, incentivizing exploration, and Markov decision processes/reinforcement learning. We will learn these techniques through the lens of their applications to pricing and auction theory, automatic bidding, recommendation systems, calibrations in forecast, and design of clinical trials/experiments. The topic of each lecture is based on one particular application domain.

 

 

This is a PhD-level course for students with strong quantitative and mathematical backgrounds. The course doesn't have an official prerequisite, but (i) basic graduate-level probability and game theory classes as prerequisites are recommended, and (ii) familiarity with learning theory and convex optimization (at the level of BUSN 36920/36931BUSN 36919, and/or similar courses at TTIC) will be helpful. Students should be comfortable with probability theory, continuous and discrete optimization, and basic algorithms. PhD students only (strict). 

 

  • PhD - students only
  • No pass/fail grades
Description and/or course criteria last updated: June 05 2024
SCHEDULE
  • Spring 2025
    Section: 36922-50
    Day/Time: TBD
    Building: TBD
    Location: TBD
    In-Person Only