Skip to content

Author

Qi-Xin Zhang

We have 8 of 21 papers

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

Preprint Oct 2026

When Weak Submodularity Meets Matroids: How Does Standard Greedy Behave?

Weakly submodular maximization finds numerous applications in machine learning, data mining and statistics. In particular, under a cardinality constraint, the standard greedy algorithm is known to attain the tight $(1-e^{-\gamma})$-approximation guarantee, where $\gamma$ denotes the submodularity ratio. However, when c...

Qi-Xin Zhang, Shi Fu, Shengminjie Chen et al. · 0 citations
Preprint Oct 2026

Structural Dual Adaptation for Safe Reinforcement Learning

Primal-dual methods enforce safety constraints in reinforcement learning through Lagrangian relaxation. For a fixed policy, the exact bounded multiplier response exhibits bang-bang switching at the constraint boundary. Practical gradient updates can oscillate through coupling with policy optimization. We propose Struct...

Run-Sheng Yu, Zhuo-Yang Song, Zengde Deng et al. · 0 citations
#artificial intelligence Preprint Oct 2026

Probabilistic Multi-Source Data Selection via Learnable Categorical Priors: Variance Reduction and Guaranteed Derandomization

Bilevel data selection is a fundamental task with numerous applications in machine learning and statistics. A common strategy for tackling this problem is to relax the original bilevel combinatorial optimization into a continuous one. However, existing methods, including 0-1 relaxation and probabilistic relaxation, sti...

Shi-Zhan Cai, Qi-Xin Zhang, Si-Yuan Ma et al. · 0 citations
#machine learning Preprint Sep 2026

Poisson Exchange Beyond Submodularity: Effective Approximation Algorithms for Offline and Online Subset Selection over Matroids

Over the past decade, a growing body of research has shown that $\gamma$-weak submodularity broadly arises in numerous subset selection tasks, including feature selection, neural network pruning, and video summarization. Despite its prevalence, maximizing a $\gamma$-weakly submodular function subject to a general matro...

Shi Fu, You-Ming Qiao, Da-Cheng Tao et al. · 1 citation
#machine learning Preprint Sep 2026

A Sharp Barrier for Consistent Submodular Maximization: Any Improvement over $2-\sqrt{2}$ Entails Exponential Queries or Linear Recourse

This work proves that the supremum approximation achievable with polynomially many value queries and worst-case constant recourse is 1-1/e-\varepsilon, and determines the exact curvature-dependent threshold $1-(\sqrt2-1)\vartheta$ for weighted coverage with weighted coverage with $O(\varepsilon^{-1})$ recourse.

Shi Fu, Qi-Xin Zhang, Da-Cheng Tao · 0 citations
#machine learning Preprint Sep 2026

Restricted Eigenvalues Beyond Gaussian Width: Threshold Occupancy under Heavy Tails

Restricted eigenvalue (RE) bounds govern stable recovery by norm-regularized estimators. For isotropic sub-Gaussian measurements, the benchmark sample size is $1+w(A)^2$, where $w(A)$ is the Gaussian width of the normalized descent cone. The COLT 2015 open-problem note (Banerjee et al., 2015) asked whether the same law...

Shi Fu, Hui-Bo Xu, Qi-Xin Zhang et al. · 0 citations
Preprint Jul 2026

Stochastic Pauli-path simulator for large-scale quantum optimization

The stochastic Pauli-path simulator (SPPS), a computational framework for large-scale quantum optimization that enables unbiased stochastic gradient estimation via Pauli-path sampling across optimization iterations, is proposed.

Kai-Ning Zhang, Xin-Biao Wang, Kun-Sheng Li et al. · 0 citations
#machine learning Preprint Aug 2026

Feature Priming in Online Linear Regression: Sparse-Regret Lower Bounds and a Tight Univariate Rate

This analysis identifies a common obstruction: cheap nuisance interpolation causes the refit to underweight the truly predictive coordinate, and an exact target-mass identity and a two-sign argument turn this effect into clipped prediction loss.

Huibo Xu, Shi Fu, Qixin Zhang et al. · 0 citations

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.