• Seth Neel, Michael Kearns, Aaron Roth, Matthew Joseph, Jamie morgenstern (2016), Fairness in Linear Bandit Problems, . Description
  Conference talk at FATML 2016 (fatml.org). Recording and pdf available at link.
• Seth Neel, Michael Kearns, Aaron Roth, Matthew Joseph (Under Review), Rawlsian Fairness for Machine Learning.

Past Courses

• AMCS9999 - Ind Study & Research

  Study under the direction of a faculty member.

• CAMB9950 - Dissertation

  Ph.D. students enroll in this course after passing their candidacy exam. They work on their dissertation full-time under the guidance of their dissertation supervisor and other members of their dissertation committee.

• CIS0099 - Ugrad Resrch/Ind Study

  An opportunity for the student to become closely associated with a professor (1) in a research effort to develop research skills and techniques and/or (2) to develop a program of independent in-depth study in a subject area in which the professor and student have a common interest. The challenge of the task undertaken must be consistent with the student's academic level. To register for this course, the student must submit a detailed proposal, signed by the independent study supervisor, to the SEAS Office of Academic Programs (111 Towne) no later than the end of the "add" period. Prerequisite: A maximum of 2 c.u. of CIS 0099 may be applied toward the B.A.S. or B.S.E. degree requirements.

• CIS3990 - Special Topics

  Visit the CIS department website for descriptions of available Special Topics classes.

• CIS4100 - Senior Thesis

  The goal of a Senior Thesis project is to complete a major research project under the supervision of a faculty member. The duration of the project is two semesters. To enroll in CIS 4100, students must develop an abstract of the proposed work, and a member of the CIS graduate group must certify that the work is suitable and agree to supervise the project; a second member must agree to serve as a reader. At the end of the first semester, students must submit an intermediate report; if the supervisor and reader accept it, they can enroll in CIS 4110. At the end of the second semester, students must describe their results in a written thesis and must present them publicly, either in a talk at Penn or in a presentation at a conference or workshop. Grades are based on the quality of the research itself (which should ideally be published or at least of publishable quality), as well as on the quality of the thesis and the oral presentation. The latter are evaluated jointly by the supervisor and the reader. The Senior Thesis program is selective, and students are generally expected to have a GPA is in the top 10-20% to qualify. Senior Theses are expected to integrate the knowledge and skills from earlier coursework; because of this, students are not allowed to enroll in CIS 4100 before their sixth semester.

• CIS4230 - Ethical Algorithm Design

  This class introduces aspiring data science technologists to the spectrum of ethical concerns, focusing on social norms like fairness, transparency and privacy. It introduces technical approaches to a number of these problems, including by hands-on examination of the tradeoffs in fairness and accuracy in predictive technology, introduction to differential privacy, and overview of evaluation conventions for predictive technology. It also provides guidelines for examining system training data for bias, representation (of race, gender and other characteristics) and ecological validity. Equipped with this knowledge, students will learn how to conduct informed analysis of the usefulness of predictive systems; they will audit for ethical concerns papers from the contemporary top artificial intelligence venues and the ongoing senior design projects.

• CIS5230 - Ethical Algorithm Design

  This class introduces aspiring data science technologists to the spectrum of ethical concerns, focusing on social norms like fairness, transparency and privacy. It introduces technical approaches to a number of these problems, including by hands-on examination of the tradeoffs in fairness and accuracy in predictive technology, introduction to differential privacy, and overview of evaluation conventions for predictive technology. It also provides guidelines for examining system training data for bias, representation (of race, gender and other characteristics) and ecological validity. Equipped with this knowledge, students will learn how to conduct informed analysis of the usefulness of predictive systems; they will audit for ethical concerns papers from the contemporary top artificial intelligence venues and the ongoing senior design projects. Preparation for this course would include taking CIS 1210 or equivalent knowledge.

• CIS5970 - Master's Thesis Research

  For students working on an advanced research leading to the completion of a Master's thesis.

• CIS5990 - Master's Indep Study

  For master's students studying a specific advanced subject area in computer and information science. Involves coursework and class presentations. A CIS 5990 course unit will invariably include formally gradable work comparable to that in a CIS 500-level course. Students should discuss with the faculty supervisor the scope of the Independent Study, expectations, work involved, etc.

• CIS6250 - Thry of Machine Learning

  This course is an introduction to the theory of Machine Learning, a field which attempts to provide algorithmic, complexity-theoretic and statistical foundations to modern machine learning. The focus is on topics in machine learning theory for researchers and students in artificial intelligence, neural networks, theoretical computer science, and statistics.

• CIS9990 - Master's Thesis

  For students working on an advanced research program leading to the completion of master's thesis requirements.

• CIS9999 - Independent Study Research

  For Computer and Information Science doctoral students studying a specific advanced subject area. Students should discuss with the faculty supervisor the scope of the independent study/research and know the expectations and work involved.

• NETS1120 - Networked Life

  How do infectious diseases spread? Why do some memes spread virally while others do not? Why do some teams or organizations perform better than others? Are we all really connected by six degrees of separation and, if so, how is that are our neighborhoods, workplaces, and social circles are so segregated? The answers to these questions and many more are all part of Network Science, a fascinating subject at the intersection of many disciplines, including computer science, communications, psychology, sociology, mathematics, and economics. This course will provide an introduction to the technical language of network science as well as to a collection of applications such as mathematical epidemiology, social contagion, games of cooperation and coordination, and collective problem solving.

• STAT9950 - Dissertation

  Dissertation

Knowledge @ Wharton

• Where Does ESG Stand Today?, Knowledge @ Wharton - 04/18/2025
• How Today’s Entrepreneurs Create Value Through Innovation and Grit, Knowledge @ Wharton - 04/16/2025
• Globalization of Sports With Ethan Strauss, Knowledge @ Wharton - 04/16/2025
• How to Teach Your Child About Financial Literacy, Knowledge @ Wharton - 04/15/2025
• Bridging the Retirement Gap | Kent Smetters, Knowledge @ Wharton - 04/15/2025
• Do Impact Investors Prioritize Financial Returns Over Social Impact?, Knowledge @ Wharton - 04/14/2025
• How U.S. Tariffs Are Upending Supply Chains, Knowledge @ Wharton - 04/14/2025
• The Hidden Economic Costs of U.S. Tariff Policy, Knowledge @ Wharton - 04/14/2025
• Basel III, Crypto, and the Future of Banking Oversight, Knowledge @ Wharton - 04/11/2025
• The New Tariff Era: Global Supply Chains Under Pressure, Knowledge @ Wharton - 04/09/2025

• Seth Neel, Michael Kearns, Aaron Roth, Matthew Joseph, Jamie morgenstern (2016), Fairness in Linear Bandit Problems, . Description
  Conference talk at FATML 2016 (fatml.org). Recording and pdf available at link.
• Seth Neel, Michael Kearns, Aaron Roth, Matthew Joseph (Under Review), Rawlsian Fairness for Machine Learning.

Past Courses

• AMCS9999 - Ind Study & Research

  Study under the direction of a faculty member.

• CAMB9950 - Dissertation

  Ph.D. students enroll in this course after passing their candidacy exam. They work on their dissertation full-time under the guidance of their dissertation supervisor and other members of their dissertation committee.

• CIS0099 - Ugrad Resrch/Ind Study

  An opportunity for the student to become closely associated with a professor (1) in a research effort to develop research skills and techniques and/or (2) to develop a program of independent in-depth study in a subject area in which the professor and student have a common interest. The challenge of the task undertaken must be consistent with the student's academic level. To register for this course, the student must submit a detailed proposal, signed by the independent study supervisor, to the SEAS Office of Academic Programs (111 Towne) no later than the end of the "add" period. Prerequisite: A maximum of 2 c.u. of CIS 0099 may be applied toward the B.A.S. or B.S.E. degree requirements.

• CIS3990 - Special Topics

  Visit the CIS department website for descriptions of available Special Topics classes.

• CIS4100 - Senior Thesis

  The goal of a Senior Thesis project is to complete a major research project under the supervision of a faculty member. The duration of the project is two semesters. To enroll in CIS 4100, students must develop an abstract of the proposed work, and a member of the CIS graduate group must certify that the work is suitable and agree to supervise the project; a second member must agree to serve as a reader. At the end of the first semester, students must submit an intermediate report; if the supervisor and reader accept it, they can enroll in CIS 4110. At the end of the second semester, students must describe their results in a written thesis and must present them publicly, either in a talk at Penn or in a presentation at a conference or workshop. Grades are based on the quality of the research itself (which should ideally be published or at least of publishable quality), as well as on the quality of the thesis and the oral presentation. The latter are evaluated jointly by the supervisor and the reader. The Senior Thesis program is selective, and students are generally expected to have a GPA is in the top 10-20% to qualify. Senior Theses are expected to integrate the knowledge and skills from earlier coursework; because of this, students are not allowed to enroll in CIS 4100 before their sixth semester.

• CIS4230 - Ethical Algorithm Design

  This class introduces aspiring data science technologists to the spectrum of ethical concerns, focusing on social norms like fairness, transparency and privacy. It introduces technical approaches to a number of these problems, including by hands-on examination of the tradeoffs in fairness and accuracy in predictive technology, introduction to differential privacy, and overview of evaluation conventions for predictive technology. It also provides guidelines for examining system training data for bias, representation (of race, gender and other characteristics) and ecological validity. Equipped with this knowledge, students will learn how to conduct informed analysis of the usefulness of predictive systems; they will audit for ethical concerns papers from the contemporary top artificial intelligence venues and the ongoing senior design projects.

• CIS5230 - Ethical Algorithm Design

  This class introduces aspiring data science technologists to the spectrum of ethical concerns, focusing on social norms like fairness, transparency and privacy. It introduces technical approaches to a number of these problems, including by hands-on examination of the tradeoffs in fairness and accuracy in predictive technology, introduction to differential privacy, and overview of evaluation conventions for predictive technology. It also provides guidelines for examining system training data for bias, representation (of race, gender and other characteristics) and ecological validity. Equipped with this knowledge, students will learn how to conduct informed analysis of the usefulness of predictive systems; they will audit for ethical concerns papers from the contemporary top artificial intelligence venues and the ongoing senior design projects. Preparation for this course would include taking CIS 1210 or equivalent knowledge.

• CIS5970 - Master's Thesis Research

  For students working on an advanced research leading to the completion of a Master's thesis.

• CIS5990 - Master's Indep Study

  For master's students studying a specific advanced subject area in computer and information science. Involves coursework and class presentations. A CIS 5990 course unit will invariably include formally gradable work comparable to that in a CIS 500-level course. Students should discuss with the faculty supervisor the scope of the Independent Study, expectations, work involved, etc.

• CIS6250 - Thry of Machine Learning

  This course is an introduction to the theory of Machine Learning, a field which attempts to provide algorithmic, complexity-theoretic and statistical foundations to modern machine learning. The focus is on topics in machine learning theory for researchers and students in artificial intelligence, neural networks, theoretical computer science, and statistics.

• CIS9990 - Master's Thesis

  For students working on an advanced research program leading to the completion of master's thesis requirements.

• CIS9999 - Independent Study Research

  For Computer and Information Science doctoral students studying a specific advanced subject area. Students should discuss with the faculty supervisor the scope of the independent study/research and know the expectations and work involved.

• NETS1120 - Networked Life

  How do infectious diseases spread? Why do some memes spread virally while others do not? Why do some teams or organizations perform better than others? Are we all really connected by six degrees of separation and, if so, how is that are our neighborhoods, workplaces, and social circles are so segregated? The answers to these questions and many more are all part of Network Science, a fascinating subject at the intersection of many disciplines, including computer science, communications, psychology, sociology, mathematics, and economics. This course will provide an introduction to the technical language of network science as well as to a collection of applications such as mathematical epidemiology, social contagion, games of cooperation and coordination, and collective problem solving.

• STAT9950 - Dissertation

  Dissertation

Knowledge @ Wharton

• Where Does ESG Stand Today?, Knowledge @ Wharton - 04/18/2025
• How Today’s Entrepreneurs Create Value Through Innovation and Grit, Knowledge @ Wharton - 04/16/2025
• Globalization of Sports With Ethan Strauss, Knowledge @ Wharton - 04/16/2025
• How to Teach Your Child About Financial Literacy, Knowledge @ Wharton - 04/15/2025
• Bridging the Retirement Gap | Kent Smetters, Knowledge @ Wharton - 04/15/2025
• Do Impact Investors Prioritize Financial Returns Over Social Impact?, Knowledge @ Wharton - 04/14/2025
• How U.S. Tariffs Are Upending Supply Chains, Knowledge @ Wharton - 04/14/2025
• The Hidden Economic Costs of U.S. Tariff Policy, Knowledge @ Wharton - 04/14/2025
• Basel III, Crypto, and the Future of Banking Oversight, Knowledge @ Wharton - 04/11/2025
• The New Tariff Era: Global Supply Chains Under Pressure, Knowledge @ Wharton - 04/09/2025