1 h 4 min
Seminar, Hosted by Simons Institute for the Theory of Computing, UC Berkeley
Let’s Stop Leaving Money on the Table | Richard M. Karp Distinguished Lecture
Hebrew University of Jerusalem
Recording
Abstract
Katrina Ligett explores why learning theory can make pessimistic predictions even when practical systems succeed. Instead of analysing only worst-case algorithms and data, she proposes reformulating questions around properties that explain algorithmic success and instance-specific performance. Examples in generalisation and privacy illustrate how these perspectives could narrow the gap between theory and empirical practice and create new mathematical questions.