arXiv subjects

Minbo Gao

Publications and source records attributed to Minbo Gao.

At least 37 records · Page 2Linked to original sources

arXiv2026

Gate-Efficient Implementation of the Query-Optimal Time-Dependent Hamiltonian Simulation

The query-optimal algorithm of [CGWZ26] for general time-dependent Hamiltonian simulation uses $$ q = O\left( αT + \frac{\log(1/\varepsilon)}{\log\left(e + \log(1/\varepsilon)/(αT) \right)} \right) $$ queries to $\mathrm{HAM\mbox{-}T}$ within $\varepsilon$ error for a Lipschitz-continuous time-dependent Hamiltonian $H(t)$ on $[0,T]$ satisfying $\left\lVert H(t)\right\rVert\leqα$. However, its direct circuit implementation incurs a substantially larger gate overhead. In this note, we give an implementation of the same algorithm that retains its optimal query complexity and uses $$ O\left[ q \left( a + \log\left(1 + \frac{T(α+ βT)}{\varepsilon} \right) \right) \right] $$ one- and two-qubit gates, where $a$ is the number of block-encoding ancilla qubits and $β$ is the Lipschitz constant of $H$. The main ingredient is an exact dyadic factorization of the ordered update product in the underlying one-query transducer.

quant-ph↗

arXiv2026

Quantum Maximum Entropy Inference and Hamiltonian Learning

Maximum entropy inference and learning of graphical models are pivotal tasks in learning theory and optimization. This work extends algorithms for these problems, including generalized iterative scaling (GIS) and gradient descent (GD), to the quantum realm. While the generalization, known as quantum iterative scaling (QIS), is straightforward, the key challenge lies in the non-commutative nature of quantum problem instances, rendering the convergence rate analysis significantly more challenging than the classical case. Our principal technical contribution centers on a rigorous analysis of the convergence rates, involving the establishment of both lower and upper bounds on the spectral radius of the Jacobian matrix for each iteration of these algorithms. Furthermore, we explore quasi-Newton methods to enhance the performance of QIS and GD. Specifically, we propose using Anderson mixing and the L-BFGS method for QIS and GD, respectively. These quasi-Newton techniques exhibit remarkable efficiency gains, resulting in orders of magnitude improvements in performance. As an application, our algorithms provide a viable approach to designing Hamiltonian learning algorithms.

cs.LG↗

arXiv2026

Binary Quantized Neural Network Training Is W[1]-Hard Parameterized by Input and Output Dimensions

Ganian et al. (ICLR 2026) proved that quantized neural network training is fixed-parameter tractable when parameterized jointly by architecture treewidth, input dimension $α$, and output dimension $ω$, and left open whether $α+ω$ alone yields fixed-parameter tractability. We prove that 2-QNNT is W[1]-hard parameterized by $α+ω$. The hardness already holds with zero error on $D_k=\{(ξ^{(r)},ξ^{(r)}):0\le r\le k\}$, where every input equals its target, $|D_k|=α=ω=k+1$, and the examples form a coordinatewise prefix chain. It also holds when every non-source bias is fixed to zero. Under the Exponential Time Hypothesis, no algorithm runs in $f(α+ω)|I|^{o(α+ω)}$ for any computable $f$. The reduction starts from DAG edge-disjoint paths, converts edge capacity to vertex capacity with a directed line graph, and normalizes the result into a valid layered architecture. The key structural step is a one-flip routing equivalence: on the prefix-chain inputs, nonnegative binary weights make every activation monotone, and each required output transition has a weight-one predecessor making the same transition. Iterating this relation backward extracts a path from the unique changing input, while different transitions yield vertex-disjoint paths. In particular, every neuron on these inputs has only $k+1$ possible activation profiles.

cs.LG↗

arXiv2026

Exact Minimax One-Bit Unbiased Compression: Heavy-Tail Necessity and Finite-Randomness Approximation

A pointwise-unbiased one-bit compressor reconstructs every real input in expectation while transmitting one bit. For a scalar source $P$ with CDF $F$, mean $m$, and $\mathcal J(P)=\int_{\mathbb R}\sqrt{F(r)(1-F(r))}\,dr$, we prove that the infimum of the source-averaged reconstruction second moment over all public-coin one-bit codes unbiased on $\mathbb R$ is $m^2+\mathcal J(P)^2$. For regular full-support sources, a distribution-centered random-threshold code attains this value; a converse over arbitrary randomized binary encoders and an equality analysis characterize every attaining code up to null sets, bit relabeling, and public-seed refinement. For the Gaussian location family $\mathcal N(μ,σ^2)$ with $|μ|\le cσ$, the equal prior on the endpoint means is least favorable and the minimax value is $σ^2Λ_c^2$. Exact Gaussian minimax optimality forces a critical heavy tail: at the endpoint means, absolute moments are finite exactly for $p<3$, and $\Pr(W>t)=Θ(t^{-3}/\sqrt{\log t})$. A Cauchy-mixture robustification inflates the second moment by at most $1/(1-η)$ while making every positive-order absolute moment finite. Finite-support public randomness with finite decoder means cannot achieve exact unbiasedness on $\mathbb R$, but a bounded-output approximation using exactly $R$ shared random bits has explicit bias and second-moment bounds converging to the minimax constant. Finally, coordinate allocation communicates exactly $B$ bits per Gaussian-gradient query. On Kim's continuous quadratic hard family, the expected optimization guarantee matches the lower bound in its dependence on $(σ,d,B,\varepsilon)$, and a finite-variance high-probability bound incurs only a logarithmic confidence factor.

cs.LG↗

arXiv2026

Depth Enables Local Entropy: Quadratic Depth Dependence in Deep Variation-Norm ReLU Regression

We study Gaussian regression over the explicit vector-valued Parhi--Nowak deep-RBV^2 architecture with depth L, width w, layer-sum variation budget A, and output bound B. For this O(L w^2)-parameterized architecture, the known lower and upper bounds differ by one factor of depth. We construct a local packing showing that the quadratic depth dependence is intrinsic under an explicit sample-size-dependent radius condition. The packing has log-cardinality Omega(L^2 w^2 log w); its codewords lie in an O(lambda) L^2 ball and are pairwise Omega(lambda)-separated. The main ingredients are a bias-corrected bounded-coefficient approximation theorem and balanced amplification: multiplying a depth-D ReLU network by q can be implemented using one constant channel so that every coefficient grows by only q^(1/D). Translation to vector-valued RBV^2 blocks then has layer-sum cost O(D w^2 q^(1/D)). Gaussian Fano yields a radius-explicit lower bound governed by the output, testing, and representation scales. Under A=B=R, sigma proportional to R, and the stated radius condition, this gives minimax risk at least of order L^2 w^2 log(w) R^2/n. A pseudodimension-based finite-net upper bound gives O-tilde(L^2 w^2 R^2/n) for unbounded Gaussian responses. Thus the minimax risk has quadratic polynomial dependence on depth, up to logarithmic factors, and exhibits a transition to representation-limited behavior at smaller radius.

cs.AI↗

arXiv2026

Polynomial-Time Singular Witnesses for Non-SNS Sign Patterns

Sign-nonsingularity asks whether every real matrix with prescribed entry signs is nonsingular. Polynomial-time algorithms recognize square sign-nonsingular patterns through their connection with even directed cycles, but recognition does not itself produce an exact numerical witness in the negative case. We give a deterministic polynomial-time algorithm that, for any square sign pattern $A$, either reports that $A$ is sign-nonsingular or outputs $B\in\mathbb{Z}^{n\times n}$ and $z\in\mathbb{Z}^n\setminus\{0\}$ such that $\operatorname{sgn}(B)=A$ and $Bz=0$. After normalizing a perfect matching, an even directed cycle yields two determinant terms of opposite signs. Making either term dominant produces endpoint realizations with opposite determinant signs. Changing their magnitudes one coordinate at a time exposes an affine sign-changing step, whose zero is rational; clearing its denominator gives the integer witness. Entries of $B$ have $O(n^2\log n)$ bits, and entries of $z$ have $O(n^3\log n)$ bits. The result settles Conjecture 14.12.4 in the Handbook of Satisfiability.

cs.DS↗

arXiv2026

Time-Dependent Hamiltonian Simulation with Optimal Query Complexity

We give a query-optimal algorithm for simulating a general $n$-qubit time-dependent Hamiltonian $H(t)$ on $[0,T]$, assuming that $H$ is Lipschitz continuous and $\|H(t)\|\leqα$. In the standard $\mathrm{HAM\mbox{-}T}$ access model, the algorithm approximates the time-ordered propagator $U_H(T)$ to error $\varepsilon$ using $$ O\left( αT+\frac{\log(1/\varepsilon)} {\log(e+\log(1/\varepsilon)/(αT))} \right) $$ $\mathrm{HAM\mbox{-}T}$ queries. This matches the known query lower bound for time-independent Hamiltonians, showing that time dependence incurs no asymptotic query overhead. Our method first constructs a one-query transducer that, given an auxiliary state, implements an approximation to $U_H(T)$ and returns the state unchanged. A weighted combination of circuits that apply the transducer different numbers of times makes the error caused by omitting this state decay factorially, yielding the stated optimal precision dependence. For time-independent Hamiltonians, the same method also gives a query-optimal alternative to qubitization.

quant-ph↗

arXiv2026

No-Go Theorems for Quantum Transport Metrics from Fixed Cost Operators

Coupling-based quantum optimal transport generalizes classical optimal transport by representing transport plans as bipartite states with prescribed marginals and evaluating their cost as the expectation of a fixed Hermitian operator. Friedland et al. [Phys. Rev. Lett. 129, 110402 (2022)] conjectured that the square root of the optimal cost associated with the SWAP projector is a metric in every dimension and that this property persists for nearby quantum cost matrices. Miller [arXiv:2607.07764] disproved both conjectures by constructing explicit diagonal qutrit counterexamples. Building on his analysis, we prove a uniform no-go theorem for standard couplings. In every dimension $d\geq3$, no fixed cost operator makes either the optimal cost or its square root a metric, with violations occurring already among commuting states. The obstruction persists under stabilization of the SWAP cost. For channel-induced couplings, global nonnegativity and vanishing self-cost force the cost operator to be zero, precluding point separation when $d\geq2$. Taken together, these no-go results show that fixed-cost coupling formulations do not lead to metrics on the full quantum state space.

quant-ph↗

arXiv2026

A Correlation-Gap Bound for Nonlinear Gaussian PCA

Principal component analysis (PCA) is optimal for the linear reconstruction of Gaussian data, a foundational property underlying its central role in algorithms and signal processing. Its nonlinear analogue, however, is notoriously subtle: in 2011, Mallat and Zeitouni conjectured that the Karhunen--Loève (KL) basis remains optimal even when the retained coordinates are chosen adaptively per sample, a property that would theoretically justify the ubiquitous pipeline of PCA followed by sparse thresholding. In this paper, we establish a $1+O(1/\sqrt{d})$-approximate version of the retained-energy form of the Mallat--Zeitouni conjecture, showing that the KL basis is within this factor of the optimal basis. This dimension-free comparison depends only on the number of retained coordinates and shows that the possible advantage of optimizing over all orthonormal bases vanishes as $d$ grows. It complements the universal-constant reconstruction-error comparison of Litvak and Tikhomirov (Ann. Appl. Probab., 2018), while providing a comparison naturally suited for algorithmic analysis. Our proof rests on a clean, conceptual reduction: we relax arbitrary rotations to a deterministic threshold bound via Schur--Horn majorization, and identify the remaining loss with the correlation gap of the rank-$d$ uniform matroid over Gaussian level sets.

cs.DS↗

arXiv2026

Complete Relational Logic for Infinite-Dimensional Quantum Programs with Unbounded Assertions

We present sound and complete relational program logics for infinite-dimensional quantum and classical-quantum programs. The logics model assertions as self-adjoint unbounded linear relations, which simultaneously support quantitative and qualitative reasoning. Our main theoretical results include new convergence theorems and infinite-dimensional duality theorems for infinite-dimensional quantum states, which we use to establish completeness.

quant-ph↗

arXiv2026

Quantum Multi-Level Estimation of Functionals of Discrete Distributions

We propose a quantum multi-level estimation framework for a functional $\sum_{i=1}^n f(p_i)$ of a discrete distribution $(p_i)_{i=1}^n$. We partition the values $p_i$ into logarithmically many intervals whose length decays exponentially. For each interval, we perform non-destructive singular value discrimination to isolate the relevant $p_i$, enabling adaptive estimation of the partial sum over this interval. Unlike previous variable-time approaches, our method avoids high control overhead and requires only constant extra ancilla qubits. As an application, we present efficient quantum estimators for the $q$-Tsallis entropy of discrete distributions. Specifically: (i) For $q > 1$, we obtain a near-optimal quantum algorithm with query complexity $\tildeΘ(1/\varepsilon^{\max\{1/(2(q-1)), 1\}})$, improving the prior best $O(1/\varepsilon^{1+1/(q-1)})$ due to Liu and Wang (SODA 2025; IEEE Trans. Inf. Theory 2026). (ii) For $0 < q < 1$, we obtain a quantum algorithm with query complexity $\tilde{O}(n^{1/q-1/2}/\varepsilon^{1/q})$, exhibiting a quantum speedup over the near-optimal classical estimators due to Jiao, Venkat, Han, and Weissman (IEEE Trans. Inf. Theory 2017). Our results achieve, to our knowledge, the first near-optimal quantum estimators for parameterized $q$-entropy for non-integer $q$.

quant-ph↗

arXiv2026

On Estimating the Quantum Tsallis Relative Entropy

The relative entropy between quantum states quantifies their distinguishability. The estimation of certain relative entropies has been investigated in the literature, e.g., the von Neumann relative entropy and sandwiched Rényi relative entropy. In this paper, we present a comprehensive study of the estimation of the quantum Tsallis relative entropy. We show that for any constant $α\in (0, 1)$, the $α$-Tsallis relative entropy between two quantum states of rank $r$ can be estimated with sample complexity $\operatorname{poly}(r)$, which can be made more efficient if we know their state-preparation circuits. As an application, we obtain an approach to tolerant quantum state certification with respect to the quantum Hellinger distance with sample complexity $\widetilde{O}(r^{3.5})$, which exponentially outperforms the folklore approach based on quantum state tomography when $r$ is polynomial in the number of qubits. In addition, we show that the quantum state distinguishability problems with respect to the quantum $α$-Tsallis relative entropy and quantum Hellinger distance are $\mathsf{QSZK}$-complete in a certain regime, and they are $\mathsf{BQP}$-complete in the low-rank case.

quant-ph↗

arXiv2026

Lévy-Khintchine Structure Enables Fast-Forwardable Lindbladian Simulation

Simulation of open quantum systems is an area of active research in quantum algorithms. In this work, we revisit the connection between Markovian open-system dynamics and averages of Hamiltonian real-time evolutions, which we refer to as Hamiltonian twirling channels. By applying the Lévy-Khintchine representation theorem, we clarify when and how a dissipative dynamics can be realized using Hamiltonian twirling channels. Guided by the general theory, we explore Hamiltonian twirling with Gaussian, compound Poisson and symmetric stable distributions and their algorithmic implications. These give wide classes of Lindbladians that can be simulated in $Θ(t^{1/α})$ Hamiltonian simulation time without any extra ancilla or other quantum gates for $1\le α\le 2$. Moreover, we prove that these time complexities are asymptotically optimal using an information theoretic approach, which, to the best of our knowledge, is the first result of lower bounds on fast-forwarding simulation algorithms.

quant-ph↗

arXiv2025

Scalable Quantum Error Mitigation with Neighbor-Informed Learning

Noise in quantum hardware is the primary obstacle to realizing the transformative potential of quantum computing. Quantum error mitigation (QEM) offers a promising pathway to enhance computational accuracy on near-term devices, yet existing methods face a difficult trade-off between performance, resource overhead, and theoretical guarantees. In this work, we introduce neighbor-informed learning (NIL), a versatile and scalable QEM framework that unifies and strengthens existing methods such as zero-noise extrapolation (ZNE) and probabilistic error cancellation (PEC), while offering improved flexibility, accuracy, efficiency, and robustness. NIL learns to predict the ideal output of a target quantum circuit from the noisy outputs of its structurally related ``neighbor'' circuits. A key innovation is our 2-design training method, which generates training data for our machine learning model. In contrast to conventional learning-based QEM protocols that create training circuits by replacing non-Clifford gates with uniformly random Clifford gates, our approach achieves higher accuracy and efficiency, as demonstrated by both theoretical analysis and numerical simulation. Furthermore, we prove that the required size of the training set scales only \emph{logarithmically} with the total number of neighbor circuits, enabling NIL to be applied to problems involving large-scale quantum circuits. Our work establishes a theoretically grounded and practically efficient framework for QEM, paving a viable path toward achieving quantum advantage on noisy hardware.

quant-ph↗

arXiv2025

Quantum Hamiltonian Certification

We formalize and study the Hamiltonian certification problem. Given access to $e^{-\mathrm{i} Ht}$ for an unknown Hamiltonian $H$, the goal of the problem is to determine whether $H$ is $\varepsilon_1$-close to or $\varepsilon_2$-far from a target Hamiltonian $H_0$. While Hamiltonian learning methods have been extensively studied, they often require restrictive assumptions and suffer from inefficiencies when adapted for certification tasks. This work introduces a direct and efficient framework for Hamiltonian certification. Our approach achieves \textit{optimal} total evolution time $Θ((\varepsilon_2-\varepsilon_1)^{-1})$ for certification under the normalized Frobenius norm, without prior structural assumptions. This approach also extends to certify Hamiltonians with respect to all Pauli norms and normalized Schatten $p$-norms for $1\leq p\leq2$ in the one-sided error setting ($\varepsilon_1=0$). Notably, the result in Pauli $1$-norm suggests a quadratic advantage of our approach over all possible Hamiltonian learning approaches. We also establish matching lower bounds to show the optimality of our approach across all the above norms. We complement our result by showing that the certification problem with respect to normalized Schatten $\infty$-norm is $\mathsf{coQMA}$-hard, and therefore unlikely to have efficient solutions. This hardness result provides strong evidence that our focus on the above metrics is not merely a technical choice but a requirement for efficient certification. To enhance practical applicability, we develop an ancilla-free certification method that maintains the inverse precision scaling while eliminating the need for auxiliary qubits, making our approach immediately accessible for near-term quantum devices with limited resources.

quant-ph↗

arXiv2025

Quantum Speedup for Hypergraph Sparsification

Graph sparsification serves as a foundation for many algorithms, such as approximation algorithms for graph cuts and Laplacian system solvers. As its natural generalization, hypergraph sparsification has recently gained increasing attention, with broad applications in graph machine learning and other areas. In this work, we propose the first quantum algorithm for hypergraph sparsification, addressing an open problem proposed by Apers and de Wolf (FOCS'20). For a weighted hypergraph with $n$ vertices, $m$ hyperedges, and rank $r$, our algorithm outputs a near-linear size $\varepsilon$-spectral sparsifier in time $\widetilde O(r\sqrt{mn}/\varepsilon)$. This algorithm matches the quantum lower bound for constant $r$ and demonstrates quantum speedup when compared with the state-of-the-art $\widetilde O(mr)$-time classical algorithm. As applications, our algorithm implies quantum speedups for computing hypergraph cut sparsifiers, approximating hypergraph mincuts and hypergraph $s$-$t$ mincuts.

quant-ph↗

arXiv2025

Quantum Speedup for Sampling Random Spanning Trees

We present a quantum algorithm for sampling random spanning trees from a weighted graph in $\widetilde{O}(\sqrt{mn})$ time, where $n$ and $m$ denote the number of vertices and edges, respectively. Our algorithm has sublinear runtime for dense graphs and achieves a quantum speedup over the best-known classical algorithm, which runs in $\widetilde{O}(m)$ time. The approach carefully combines, on one hand, a classical method based on ``large-step'' random walks for reduced mixing time and, on the other hand, quantum algorithmic techniques, including quantum graph sparsification and a sampling-without-replacement variant of Hamoudi's multiple-state preparation. We also establish a matching lower bound, proving the optimality of our algorithm up to polylogarithmic factors. These results highlight the potential of quantum computing in accelerating fundamental graph sampling problems.

quant-ph↗

arXiv2025

Complete Quantum Relational Hoare Logics from Optimal Transport Duality

We introduce a quantitative relational Hoare logic for quantum programs. Assertions of the logic range over a new infinitary extension of positive semidefinite operators. We prove that our logic is sound, and complete for bounded postconditions and almost surely terminating programs. Our completeness result is based on a quantum version of the duality theorem from optimal transport. We also define a complete embedding into our logic of a relational Hoare logic with projective assertions.

cs.LO↗