Guidelines. Each student will prepare and present a 45-minute presentation, leaving time for questions during and after the talk. In preparing and giving your presentation, the most important point is clearly conveying the high level contributions of the paper.
By April 28th, please review the list of papers below, and email the instructors an ordered list of 3 (or more) topics that you would like to present.
Privacy
Differential Privacy and Heuristics
S. Neel, A. Roth, Z. S. Wu, How to Use Heuristics for Differential Privacy
Privacy and the law: the notion of "singling out"
A. Cohen and K. Nissim, Towards Formalizing The GDPR’s Notion of Singling Out
Applications of the Shapley Value
A. Ghorbani and J. Zou, Data Shapley: Equitable Valuation of Data for Machine Learning, ICML 2019. Talk at Simons Workshop.
S. M. Lundberg and Su-In Lee, A Unified Approach to Interpreting Model Predictions, NeuroIPS 2017. Talk on Explainable AI for Science and Medicine
Fair Allocation Problems (Game Theory)
Combinatorial Assignments I
E. Budish. The combinatorial assignment problem: Approximate competitive equilibrium from equal incomes
Combinatorial Assignments II
H. Aziz, Simultaneously Achieving Ex-ante and Ex-post Fairness
Matching Medical Interns to Hospitals in Israel
N. Alon, S. Bronfman, A. Hassidim, A. Romm, Redesigning the Israeli Medical Internship Match
Cake Cutting
S. Brânzei, and N. Nisan, The Communication Complexity of Cake Cutting
Algorithmic Fairness
More on group fairness
M. Hardt, E. Price and N. Srebro, Equality of Opportunity in Supervised Learning
Fairness using only query access to the metric
M. P. Kim, G. N. Rothblum and O. Reindold, Fairness Through Computationally-Bounded Awareness
Fair rankings
C. Dwork, M. P. Kim, O. Reingold, G. N. Rothblum, G. Yona, Learning from Outcomes: Evidence-Based Rankings
Individual fairness under composition
C. Dwork and C. Ilvento, Fairness under Composition
Economic perspectives on algorithmic fairness
A. Rambachan, J. Kleinberg, J. Ludwig, S. Mullainathan and , An Economic Perspective on Algorithmic Fairness
A. Rambachan, J. Kleinberg, S. Mullainathan, J. Ludwig , An economic approach to regulating algorithms
Fairness Dynamics
L. Hu, Y. Chen, A short-term intervention for long-term fairness in the labor market
C. Jung, S. Kannan, C. Lee, M. M. Pai, A. Roth, R. Vohra, Fair Prediction with Endogenous Behavior
L. T. Liu, S. Dean, E. Rolf, M. Simchowitz, M. Hardt, Delayed Impact of Fair Machine Learning
Overfitting
Freedman's paradox and multiple hypothesis testing
D. A. Freedman, A Note on Screening Regression Equations
Y. Binyamini and Y. Hochberg, Controlling the False Discovery Rate: A Practical and Powerful Approach to Multiple Testing
Lower bounds on adaptive data analysis
M. Hardt and J. Ullman, Preventing False Discovery in Interactive Data Analysis is Hard
T. Steinke and J. Ullman, Interactive Fingerprinting Codes and the Hardness of Preventing False Discovery
Bias in AI / natural language processing
Turing test and the Moral Machine
A. M. Turing, Computing Machinery and Intelligence
E. Awad, S. Dsouza, R. Kim, J. Schulz, J. Henrich, A. Shariff, J.-F. Bonnefon, I. Rahwan, The Moral Machine experiment
E. Awad, S. Dsouza, A. Shariff, J.-F. Bonnefon, I. Rahwan, Crowdsourcing moral machines
E. Awad, S. Dsouza, A. Shariff, I. Rahwan, J.-F. Bonnefon, Universals and variations in moral decisions made in 42 countries by 70,000 participants
Racial bias in medical predictions
E. Pierson, D. M. Cutler, J. Leskovec, S. Mullainathan, Z.Obermeyer, An algorithmic approach to reducing unexplained pain disparities in underserved populations
Z. Obermeyer, B. Powers, C. Vogeli and S. Mullainathan, Dissecting racial bias in an algorithm used to manage the health of populations
Bias in word embeddings / NLP I
T. Bolukbasi, C. Kai-Wei Chang, J. Zou, V. Saligrama, and A. Kalai. Man is to computer programmer as woman is to homemaker? Debiasing word embeddings
Y. Goldberg and H. Gonen, Lipstick on a Pig: Debiasing Methods Cover up Systematic Gender Biases in Word Embeddings But do not Remove Them
Bias in word embeddings / NLP II
A. Caliskan, J. J. Bryson and A. Narayanan, Semantics derived automatically from language corpora contain human-like biases
A. Abid, M. Farooqi and J. Zou, Persistent Anti-Muslim Bias in Large Language Models
Fairness beyond demographics
J. Chen, N. Kallus, X. Mao, G. Svacha, M. Udell, Fairness Under Unawareness: Assessing Disparity When Protected Class Is Unobserved
N. Kallus, X. Mao, A. Zhou, Assessing Algorithmic Fairness with Unobserved Protected Class Using Data Combination
Societal Issues in Natural Language Models
IBM's Debator
Slonim et al, The Debator: An autonomous debating system
Language Models: Issues and Concerns
Brown et al, GPT-3: Language Models are Few-Shot Learners
G. Marcus and E. Davis, GPT-3, Bloviator: OpenAI’s language generator has no idea what it’s talking about
E. M. Bender, T. Gebru, A. McMillan-Major, S. Shmitchell, On the Dangers of Stochastic Parrots: Can Language Models Be Too Big?
Learning with strategic agents
Learning in the face of feature manipulation
Yahav Bechavod, Katrina Ligett, Zhiwei Steven Wu, Juba Ziani, Gaming Helps! Learning from Strategic Interactions in Natural Dynamics
Learning in the face of feature manipulation
Juan C. Perdomo, Tijana Zrnic, Celestine Mendler-Dünner, Moritz Hardt: Performative Prediction
Forecast Testing
How (not) to test an expert forecaster
A. Sandroni, The Reproducible Properties of Correct Forecasts
Computational considerations in forecast testing
L. Fortnow and R. Vohra, The Complexity of Forecast Testing
K. Chung, E. Lui and Rafael Pass, Can Theories be Tested? A Cryptographic Treatment of Forecast Testing
Generating forecasts that are indistinguishable from reality
C. Dwork, M. P. Kim, O. Reingold, G. N. Rothblum and G. Yona, Outcome Indistinguishability
Cryptography and Society
Digital cash before Bitcoin
D. Chaum, A. Fiat and M. Naor, Untreaceable electronic Cash
Fail-stop signatures
T. P. Pederson and B. Pfitzmann, Fail-Stop Signatures
Crypto and the law: Repudiation of Encryption
A. Cohen and S. Park, Compelled Decryption and The Fifth Amendment: Exploring The Technical Boundaries
S. Shefler and M. Varya, Protecting Cryptography Against Compelled Self-Incrimination
Repudiation of ring signatures
S. Park and A. Sealfon, It wasn’t me! Repudiability and Unclaimability of Ring Signatures
Diversity of Opinions and Social Choice
C. Dwork, R. Kumar, M. Naor, S. Sivakumar, Rank Aggregation Methods for the Web
J. Kleinberg and M. Raghavan, Algorithmic Monoculture and Social Welfare
J. Gaitonde, J. Kleinberg and E. Tardos, Adversarial Perturbations of Opinion Dynamics in Networks