Quantum Coupon Collector

We study how efficiently a $k$-element set $S\subseteq[n]$ can be learned from a uniform superposition $|S\rangle$ of its elements. One can think of $|S\rangle=\sum_{i\in S}|i\rangle/\sqrt{|S|}$ as the quantum version of a uniformly random sample over $S$, as in the classical analysis of the ``coupon collector problem.'' We show that if $k$ is close to $n$, then we can learn $S$ using asymptotically fewer quantum samples than random samples. In particular, if there are $n-k=O(1)$ missing elements then $O(k)$ copies of $|S\rangle$ suffice, in contrast to the $\Theta(k\log k)$ random samples needed by a classical coupon collector. On the other hand, if $n-k=\Omega(k)$, then $\Omega(k\log k)$ quantum samples are~necessary. More generally, we give tight bounds on the number of quantum samples needed for every $k$ and $n$, and we give efficient quantum learning algorithms. We also give tight bounds in the model where we can additionally reflect through $|S\rangle$. Finally, we relate coupon collection to a known example separating proper and improper PAC learning that turns out to show no separation in the quantum case.

[1]  Rocco A. Servedio,et al.  Improved Bounds on Quantum Learning Algorithms , 2004, Quantum Inf. Process..

[2]  A. Rosmanis Lower Bounds on Quantum Query and Learning Graph Complexities , 2014 .

[3]  David Haussler,et al.  Learnability and the Vapnik-Chervonenkis dimension , 1989, JACM.

[4]  Rocco A. Servedio,et al.  Equivalences and Separations Between Quantum and Classical Learnability , 2004, SIAM J. Comput..

[5]  Ronald de Wolf,et al.  Two new results about quantum exact learning , 2021, Quantum.

[6]  W. Haemers,et al.  Association schemes , 1996 .

[7]  Iordanis Kerenidis,et al.  Learning with Errors is easy with quantum samples , 2017, Physical Review A.

[8]  G. Brassard,et al.  Quantum Amplitude Amplification and Estimation , 2000, quant-ph/0005055.

[9]  Andris Ambainis,et al.  Symmetry-Assisted Adversaries for Quantum State Generation , 2011, 2011 IEEE 26th Annual Conference on Computational Complexity.

[11]  Rocco A. Servedio,et al.  Quantum Algorithms for Learning and Testing Juntas , 2007, Quantum Inf. Process..

[12]  Ronald de Wolf,et al.  A Survey of Quantum Learning Theory , 2017, ArXiv.

[13]  E. Knill,et al.  Reversing quantum dynamics with near-optimal quantum and classical fidelity , 2000, quant-ph/0004088.

[14]  Amnon Ta-Shma,et al.  Adiabatic quantum state generation and statistical zero knowledge , 2003, STOC '03.

[15]  Troy Lee,et al.  Negative weights make adversaries stronger , 2007, STOC '07.

[16]  Scott Aaronson,et al.  Quantum lower bounds for approximate counting via laurent polynomials , 2019, Electron. Colloquium Comput. Complex..

[17]  Ronald de Wolf,et al.  Quantum lower bounds by polynomials , 2001, JACM.

[18]  Aleksandrs Belovs,et al.  Applications of Adversary Method in Quantum Query Algorithms , 2014, 1402.3858.

[19]  William Kretschmer,et al.  $\mathsf{QMA}$ Lower Bounds for Approximate Counting , 2019, ArXiv.

[20]  Steve Hanneke,et al.  The Optimal Sample Complexity of PAC Learning , 2015, J. Mach. Learn. Res..

[21]  Nader H. Bshouty,et al.  Learning DNF over the uniform distribution using a quantum example oracle , 1995, COLT '95.

[22]  Troy Lee,et al.  Quantum Query Complexity of State Conversion , 2010, 2011 IEEE 52nd Annual Symposium on Foundations of Computer Science.

[23]  Troy Lee,et al.  A strong direct product theorem for quantum query complexity , 2012, 2012 IEEE 27th Conference on Computational Complexity.

[24]  Ronald de Wolf,et al.  Guest Column: A Survey of Quantum Learning Theory , 2017, SIGA.

[25]  Nathan Srebro,et al.  VC Classes are Adversarially Robustly Learnable, but Only Improperly , 2019, COLT.

[26]  Leslie G. Valiant,et al.  A theory of the learnable , 1984, STOC '84.

[27]  Ronald de Wolf,et al.  Optimal Quantum Sample Complexity of Learning Algorithms , 2016, CCC.