Cynthia Dwork
where else to find them
no profile links on file
what they talk about
all 8 in the filters
where they keep going back
no series more than once — all 4 in the filters
on a stage with
all 6 in the filters
who talks about the same things
nobody close enough yet
| title | conference | date |
|---|---|---|
| HappyMap: A Generalized Multicalibration Method | ITCS 2023 | 2023-01-10 |
A postprocessing method called HappyMap algorithm maps any predictor to satisfy a new fairness/robustness condition, s-Happy Multicalibration, by iteratively… | ||
| Opening Remarks | Wrong at the Root: Racial Bias and the Tension Between Numbers and Words in Non-Internet Data | 2019-06-05 |
Overview of workshop goals and concrete tensions: theoretical tools used to audit census confidentiality tools and to set mathematical limits on fairness… | ||
| Afternoon Session: Individuals, Groups, Pattern Recognition and Rich Data | Wrong at the Root: Racial Bias and the Tension Between Numbers and Words in Non-Internet Data | 2019-06-05 |
Distinguishes group vs individual fairness, arguing individual fairness requires a task-specific metric and showing a small number of queries to a fair arbiter… | ||
| Questions and Discussion | Wrong at the Root: Racial Bias and the Tension Between Numbers and Words in Non-Internet Data | 2019-06-05 |
Panelists argue for concrete outputs: a short list of foundational papers, shared reading resources, and new venues that reward domain-specific, reproducible… | ||
| Groups and Individuals in Fairness and Probability | Privacy and the Science of Data Analysis 2019 | 2019-04-08 |
Compares group fairness to individual fairness and argues individual fairness needs a task-specific metric; cites a metric-learning breakthrough that learns… | ||
| Differential Privacy: Fundamentals to Forefront I | Cryptography Boot Camp 2015 | 2015-05-18 |
Formalizes differential privacy as outputs changing by at most an e^epsilon factor when any one person is added or removed; gives concrete mechanisms… | ||
| Differential Privacy: Fundamentals to Forefront II | Cryptography Boot Camp 2015 | 2015-05-18 |
Defines the privacy loss random variable and relaxes pure privacy to epsilon delta so composition error grows like √k (with log(1/δ) factors) instead of k… | ||
| nothing matches | ||