COOKIES: By using this website you agree that we can place Google Analytics Cookies on your device for performance monitoring. |
University of Cambridge > Talks.cam > Quantum Computing Seminar > Interactive proofs for verifying (quantum) learning and testing
Interactive proofs for verifying (quantum) learning and testingAdd to your list(s) Download to your calendar using vCal
If you have a question about this talk, please contact Tom Gur. We consider the problem of testing and learning from data in the presence of resource constraints, such as limited memory or weak data access, which place limitations on the efficiency and feasibility of testing or learning. In particular, we ask the following question: Could a resource-constrained learner/tester use interaction with a resource-unconstrained but untrusted party to solve a learning or testing problem more efficiently than they could without such an interaction? In this work, we answer this question both abstractly and for concrete problems, in two complementary ways: For a wide variety of scenarios, we prove that a resource-constrained learner cannot gain any advantage through classical interaction with an untrusted prover. As a special case, we show that for the vast majority of problems in which quantum memory is a meaningful resource, a memory-constrained quantum algorithm cannot overcome its limitations via classical communication with a memory-unconstrained quantum prover. In contrast, when quantum communication is allowed, we construct a variety of interactive proof protocols, for specific learning and testing problems, which allow memory-constrained quantum verifiers to gain significant advantages through delegation to untrusted provers. These results highlight both the limitations and potential of delegating learning and testing problems to resource-rich but untrusted third parties. This talk is part of the Quantum Computing Seminar series. This talk is included in these lists:
Note that ex-directory lists are not shown. |
Other listsBabbage Seminar Series Type the title of a new list here Centre for Smart Infrastructure & ConstructionOther talksMoving mesh methods in Firedrake Cyber security and privacy issues raised by mobile data extraction for evidential purposes. Chromatic Homotopy Theory Today 35 Years of Dependencies: Where the Central Asian Heritage Management Systems Find Themselves Three Decades On Under Independent Nation-States? Leveraging Large Language Models for Code Generation Langevin Monte Carlo Beyond Lipschitz Gradient Continuity |