Lisa Hellerstein

Lisa Hellerstein is a Professor of Computer Science and Engineering at New York University's Tandon School of Engineering. Her research interests include Approximation Algorithms, Stochastic Combinatorial Optimization, Machine Learning Theory, Boolean Functions, and Complexity Theory. Hellerstein holds a Ph.D. from the University of California at Berkeley and an A.B. from Harvard University. She has contributed to numerous publications in top-tier journals and conferences, including INFORMS Journal on Computing, ACM Transactions on Algorithms, and SIAM Journal on Computing. Her work explores theoretical and algorithmic challenges in computer science, with a focus on optimization and learning. Hellerstein is affiliated with the Algorithms and Foundations Group at NYU Tandon.

Lisa Hellerstein is a researcher at New York University with a focus on computational learning theory, algorithm design, and complexity analysis. Her work explores the theoretical foundations of machine learning, particularly in the context of query learning, PAC learning, and the challenges posed by irrelevant attributes. Hellerstein's research also addresses the complexity of learning boolean functions, such as read-once formulas and DNF expressions, and investigates the efficiency of algorithms for problems involving failure correction and data compression. Her contributions span both theoretical and applied aspects of learning theory, with an emphasis on understanding the limits and capabilities of learning models in the presence of noise and irrelevant features.