no code implementations • 11 Apr 2024 • Tom Gur, Mohammad Mahdi Jahanara, Mohammad Mahdi Khodabandeh, Ninad Rajgopal, Bahar Salamatian, Igor Shinkar
- We construct an interactive protocol for learning the $t$ largest Fourier characters of a given function $f \colon \{0, 1\}^n \to \{0, 1\}$ up to an arbitrarily small error, wherein the verifier uses $\mathsf{poly}(t)$ random examples.
no code implementations • 9 Nov 2023 • Matthias Caro, Tom Gur, Cambyse Rouzé, Daniel Stilck França, Sathyawageeswar Subramanian
Learning tasks play an increasingly prominent role in quantum information and computation.
no code implementations • 3 Dec 2020 • Srinivasan Arunachalam, Alex B. Grilo, Tom Gur, Igor C. Oliveira, Aarthi Sundaram
This result is optimal in both $\gamma$ and $T$, since it is not hard to learn any class $\mathfrak{C}$ of functions in (classical) time $T = 2^n$ (with no error), or in quantum time $T = \mathsf{poly}(n)$ with error at most $1/2 - \Omega(2^{-n/2})$ via Fourier sampling.
no code implementations • 19 Feb 2017 • Clement Canonne, Tom Gur
More accurately, we say that a tester is $k$-(round) adaptive if it makes queries in $k+1$ rounds, where the queries in the $i$'th round may depend on the answers obtained in the previous $i-1$ rounds.