Omnipredictors for constrained optimization

L Hu, IRL Navon, O Reingold… - … Conference on Machine …, 2023 - proceedings.mlr.press
The notion of omnipredictors (Gopalan, Kalai, Reingold, Sharan and Wieder ITCS 2022),
suggested a new paradigm for loss minimization. Rather than learning a predictor based on …

Classical verification of quantum learning

MC Caro, M Hinsche, M Ioannou, A Nietner… - arxiv preprint arxiv …, 2023 - arxiv.org
Quantum data access and quantum processing can make certain classically intractable
learning tasks feasible. However, quantum capabilities will only be available to a select few …

[PDF][PDF] Refining the Sample Complexity of Comparative Learning

S Ashkezari, R Urner - Proceedings of Machine …, 2025 - raw.githubusercontent.com
Comparative learning, a recently introduced variation of the PAC (Probably Approximately
Correct) framework, interpolates between the two standard extreme settings of realizable …

Generative models of huge objects

L Hu, I Livni-Navon, O Reingold - arxiv preprint arxiv:2302.12823, 2023 - arxiv.org
This work initiates the systematic study of explicit distributions that are indistinguishable from
a single exponential-size combinatorial object. In this we extend the work of Goldreich …

[KIRJA][B] Trustworthiness: Revisiting the Foundations of Machine Learning

L Hu - 2024 - search.proquest.com
As we deploy machine learning models in more and more complex and critical tasks, can we
trust that these models will work as intended in real-world settings? For example, a doctor …