We study the number of uniform quantum examples needed to exactly learn a Boolean function with at most $k$ nonzero Fourier coefficients. We give a learner with near-optimal $\widetilde{O}(k)$ sample complexity independent of the input length $n$. The learner uses only separate measurements of individual examples. This improves the previous $O(k^{3/2}\log^2 k)$ upper bound (Arunachalam, Chakraborty, Lee, Paraashar, and de Wolf, 2021). The main ingredient is a candidate set formed by symmetric differences of subsets from independent groups of Fourier samples. A multilinear majority polynomial combines unbiased random approximations into an accurate witness whose Fourier support lies in this set. Granularity then forces the set to contain the entire Fourier support, including subsets never directly sampled. For comparison, we derive the tight classical sample complexity $Θ(nk)$ by combining known sparse-recovery and lower-bound results.
AI Summary
The paper studies exact identification of Boolean functions $f:\mathbb F_2^n\to\{-1,1\}$ with at most $k$ nonzero Fourier coefficients, using independent uniform quantum examples and outputting the complete classical Fourier representation. It asks whether the previous $O(k^{3/2}\log^2 k)$ quantum sample bound can be reduced to near-linear dependence on $k$.
The main result is an $O(k\log^2 k/\log\log k)$ upper bound, independent of $n$, with success probability at least $2/3$ and constant sample complexity for bounded $k$. This establishes the previously conjectured $O(k\,\mathrm{polylog}\,k)$ bound. Each quantum example is measured separately. Independent repetition increases success to $1-\delta$ with an additional $O(\log(1/\delta))$ factor.
The learner groups Fourier samples and forms a candidate support from symmetric differences selecting at most one sample per group. Coverage is proved using analysis-only unbiased weighted parity averages, combined through the multilinear majority polynomial. Independence suppresses the mean-square error; Fourier granularity then implies that the candidate set contains every nonzero coefficient, including coefficients never directly sampled. Independent computational-basis measurements provide classical equations, and fixed-vector sparse recovery via $\ell_1$ minimization reconstructs the coefficients.
A quantum coupon-collector reduction gives an $\Omega(k\log k)$ lower bound throughout the parameter range, leaving an $O(\log k/\log\log k)$ gap. Combining existing recovery and lower-bound results also yields tight classical sample complexity $\Theta(nk)$ at constant error. The guarantees concern samples rather than polynomial-time learning: the candidate dictionary can be quasipolynomial in $k$. The model assumes uniform, noiseless examples and exact recovery.
Some signs of AI-generated textAI use disclosed
ChatGPT (model: GPT-6 Astra) was used in developing the arguments and preparing this manuscript.
Written by gpt-6.1-sol from the paper's full text. Automated: it can be wrong.
We study the number of uniform quantum examples needed to exactly learn a Boolean function with at most k nonzero Fourier coefficients. We give a learner with near-optimal O(k) sample complexity independent of the input length n. The learner uses only separate measurements of individual examples. This improves the previous O(k3/2log2k) upper bound (Arunachalam, Chakraborty, Lee, Paraashar, and de Wolf, 2021). The main ingredient is a candidate set formed by symmetric differences of subsets from independent groups of Fourier samples. A multilinear majority polynomial combines unbiased random approximations into an accurate witness whose Fourier support lies in this set. Granularity then forces the set to contain the entire Fourier support, including subsets never directly sampled. For comparison, we derive the tight classical sample complexity Θ(nk) by combining known sparse-recovery and lower-bound results.
The paper studies exact identification of Boolean functions f:F2n→{−1,1} with at most k nonzero Fourier coefficients, using independent uniform quantum examples and outputting the complete classical Fourier representation. It asks whether the previous O(k3/2log2k) quantum sample bound can be reduced to near-linear dependence on k.
The main result is an O(klog2k/loglogk) upper bound, independent of n, with success probability at least 2/3 and constant sample complexity for bounded k. This establishes the previously conjectured O(kpolylogk) bound. Each quantum example is measured separately. Independent repetition increases success to 1−δ with an additional O(log(1/δ)) factor.
The learner groups Fourier samples and forms a candidate support from symmetric differences selecting at most one sample per group. Coverage is proved using analysis-only unbiased weighted parity averages, combined through the multilinear majority polynomial. Independence suppresses the mean-square error; Fourier granularity then implies that the candidate set contains every nonzero coefficient, including coefficients never directly sampled. Independent computational-basis measurements provide classical equations, and fixed-vector sparse recovery via ℓ1 minimization reconstructs the coefficients.
A quantum coupon-collector reduction gives an Ω(klogk) lower bound throughout the parameter range, leaving an O(logk/loglogk) gap. Combining existing recovery and lower-bound results also yields tight classical sample complexity Θ(nk) at constant error. The guarantees concern samples rather than polynomial-time learning: the candidate dictionary can be quasipolynomial in k. The model assumes uniform, noiseless examples and exact recovery.
Research manuscript with PDF, LaTeX and review records. An algorithm exactly recovers every k-Fourier-sparse Boolean function with success at least 2/3 using O(k log^3(2k)) independent supplied uniform quantum examples and fixed-polynomial total computation and live space. Fresh residual estimates construct a queryable sign-majority hypothesis; known-function Fourier search and original-target certification contract missing Fourier energy. The theorem uses no target membership query or state-preparation inverse. All samples, adaptive refits and exact rational bit costs are charged. This complements Ye's smaller sample bound with a polynomial computational guarantee. No optimal logarithmic factor, practical implementation, noise robustness, exhaustive novelty, independent peer review, formal certification or BPP/BQP result is claimed. OpenAI Codex assisted derivation, source comparison, drafting and internal checking. Separate model reviews were obtained through Grok, Claude and AGY (configured with Gemini), with findings dispositioned in the archive. These are AI reviews, not independent human peer review.
As quantum computing progresses toward fault-tolerant architectures, the question of which computational tasks admit provable quantum advantages and which do not has become increasingly central. Learning theory, and in particular learning from quantum examples, provides one of the few settings in which unconditional quantum-classical separations can be established. In distribution-free (i.e., worst-case) PAC learning, existing results show that quantum examples provide no asymptotic advantage in sample complexity. In contrast, under the uniform distribution, unbounded quantum-classical separations are known for learning Fourier-sparse Boolean functions. Together, these results reveal a striking dichotomy. However, this understanding has largely been developed in the context of learning Boolean functions in the batch setting, leaving open how these phenomena extend more broadly. This thesis develops the theory of learning with quantum examples beyond the batch Boolean setting along three directions: multiclass learning, online learning, and smoothed learning. In the multiclass PAC setting, we establish upper and lower bounds on quantum sample complexity in both the realizable and agnostic regimes, finding that quantum examples continue to yield no distribution-independent separation from classical examples, with learning rates governed by the Natarajan dimension up to logarithmic factors in the label-space size. We next study online learning, where no standard framework for learning with quantum examples existed prior to this work. We provide such a model by lifting the classical online framework to one in which the adversary provides distributions over labeled examples, and then by encoding these distributions as quantum examples. We establish expected regret guarantees for binary and multiclass classification in both the realizable and agnostic settings. The central finding is that unrestricted adversarial power permits highly concentrated distributions that dequantize the learning problem. Motivated by this dequantization phenomenon, we develop a smoothed learning framework that constrains distributions to be smooth, interpolating between the concentrated-distribution regime, in which no quantum advantage exists, and the uniform-distribution regime, in which unbounded separations are known. For the class of Fourier-sparse Boolean functions, we establish the robustness of quantum Fourier sampling throughout a nontrivial near-uniform regime in the batch setting and observe that these guarantees extend naturally to the online setting. We further analyze several approaches to recovering the target function once its Fourier support has been identified and, based on these observations, formulate conjectures supporting the persistence of the unbounded quantum advantage throughout this regime. Together, these results paint a coherent picture of learning with quantum examples beyond the batch Boolean setting, showing that quantum-classical separations depend on the interplay between hypothesis class structure, distributional assumptions, and the degree of adversarial control permitted in the learning process.
We present two new results about exact learning by quantum computers. First, we show how to exactly learn a k -Fourier-sparse n -bit Boolean function from O(k1.5(logk)2) uniform quantum examples for that function. This improves over the bound of Θ~(kn) uniformly random classical examples (Haviv and Regev, CCC'15). Additionally, we provide a possible direction to improve our O~(k1.5) upper bound by proving an improvement of Chang's lemma for k -Fourier-sparse Boolean functions. Second, we show that if a concept class C can be exactly learned using Q quantum membership queries, then it can also be learned using O(Q2logQlog|C|) classical membership queries. This improves the previous-best simulation result (Servedio and Gortler, SICOMP'04) by a logQ -factor.
We study the problem of tomography for k-sparse quantum states. In contrast to classical distribution learning, where tight sample and time complexity bounds in terms of support size are well understood, no non-trivial bounds were previously shown for this problem. We give the first near optimal algorithm for learning n-qubit k-sparse pure quantum states, obtaining fidelity at least 1−ε with high probability using O~(k/ε) copies of the state and O~(kn/ε) time. Both bounds are optimal up to polylogarithmic factors. As an implication, we also obtain an algorithm with near optimal O~(kr/ε) sample complexity for learning k-sparse rank-r mixed states, via the random purification channel technique. Obtaining time complexity nearly matching the sample complexity, for r>1, remains an important open question.
We present two new results about exact learning by quantum computers. First, we show how to exactly learn a k-Fourier-sparse n-bit Boolean function from O(k^{1.5}(log k)^2) uniform quantum examples for that function. This improves over the bound of Theta~(kn) uniformly random classical examples (Haviv and Regev, CCC'15). Our main tool is an improvement of Chang’s lemma for sparse Boolean functions. Second, we show that if a concept class {C} can be exactly learned using Q quantum membership queries, then it can also be learned using O ({Q^2}/{log Q} * log|C|) classical membership queries. This improves the previous-best simulation result (Servedio-Gortler, SICOMP'04) by a log Q-factor.
We establish an unconditional super-polynomial separation between quantum and classical PAC learning of Boolean functions under the uniform distribution in the large error regime. For every advantage λ(n)=n−ω(1), we construct a concept class that a polynomial-time quantum learner learns to agreement 1/2+λ(n) with success probability at least 1−1/nk. The learner uses only quantum random examples and outputs a polynomial-size deterministic classical circuit. In contrast, no polynomial-time classical learner achieves agreement 1/2+λ(n)/nk with success probability greater than 1/nk, even with membership queries.
To achieve this, we develop a nearly-optimal quantum learner that uses quantum random examples to produce a hypothesis achieving a prescribed correlation with an arbitrary Boolean function. The learner generalizes Fourier sampling from parity hypotheses to quadratic hypotheses. While standard Fourier sampling is insensitive to the sign of the correlation, we use interference to bias sampling toward positively correlated hypotheses. This is combined with a careful analysis of the resulting distribution to boost both the learner's success probability and its agreement with the target function. We believe that the resulting quantum learning algorithm might be of independent interest.
Finally, although a robust quantum PAC learning advantage holds unconditionally in the large error regime, we note that an analogous separation between quantum and classical learning in the small error regime would imply that NP⊈BPP.