Searcharxiv⌕ Search

arXiv subjects

Zhen Zhang

Publications and source records attributed to Zhen Zhang.

At least 73 records · Page 4Linked to original sources
arXiv2026

Interpretable Factor Decomposition for Decision Intelligence in Large-Scale Financial Markets: Evidence from China's A-Share Market

We present an interpretable machine learning pipeline to decompose cross-sectional equity return predictability into auditable factor contributions. We apply an XGBoost model with TreeSHAP attribution and conduct stress testing on 3,632 Chinese A-share stocks from 2009 until 2019. On prediction, using 60-month rolling windows over 55 months of out-of-sample data, XGBoost obtains a mean AUC of 0.547 (rank IC = 0.119) and +2.38%/month (Newey-West t = 5.94; annualized Sharpe 2.23) long-short spread for the top vs bottom quintiles. This alpha is persistent after adjusting for the Carhart four-factor model (+2.31%/month; t = 7.48). On interpretation, SHAP decomposition indicates that behavioral signals (turnover and momentum) account for 58.2% of predictive attribution compared to 10.7% for valuation ratios, on average, across 50 industry groups. Ablation analysis serves to cross-validate this ranking and provides evidence that SHAP and ablation diverge in a manner that highlights feature substitutability structure that is largely invisible to either method used in isolation.

cs.LG↗
arXiv2026

Deformations and second-order rigidity of polytopes

We study deformations of polytopes that preserve edge lengths and face coplanarities. This gives rise to a notion of rigidity, for which we develop a second-order theory together with an effective algorithm for testing second-order rigidity symbolically. The strength of these new tools is demonstrated on several polytope classes, including the previously intractable regular dodecahedron, which we find to be rigid. We also find that a single tested polytope evades our techniques and will therefore provide a simple test case for future developments of tools of even higher order. This paper also contains a study of so-called edge-length perturbations. We point out connections between rigidity and the ability to realize polytopes with slightly perturbed edge lengths. To explore these connections in practice, we dedicate a section to another case study of the regular dodecahedron. We investigate the local behavior of its realization space with a view towards edge-length perturbations, singularities and generic global rigidity.

math.CO↗
arXiv2026

Interpretable vs Learned Encoders for High-Cardinality Fraud Detection

A total of seven categorical encoding methods were tested on the IEEE-CIS fraud benchmark dataset (590,540 records, 3.5% positives, 8 high-cardinality columns). The encoders were evaluated using a stratified 5-fold cross-validation (CV) with three repetitions. Five of the encoders had identical frozen LightGBM learners in the downstream phase, allowing for controlled comparisons of their performance to each other. CatBoost and TabNet were included as comparisons across paradigms using different learners. The entity embeddings produced the highest AUC-ROC (0.9612), with a statistically significant tie with that of CatBoost (0.9602) and statistically superior to tier group encoding (0.9548), whereas target encoding was only 0.0023 worse than tier group encoding and the auditor-friendly tier boundaries were maintained. Off-the-shelf TabNet did not outperform tree-based pipelines and collapsed under data scarcity. On AUC-PR, CatBoost leads (0.822 vs. 0.793); no encoder dominated both metrics. Per-column analysis confirmed the embedding advantage arises from joint multi-column representation.

cs.LG↗
arXiv2026

Reachability Analysis With Probabilistic Zonotopes: Learning Realized Disturbances and Refining Aleatory Uncertainty

This paper develops a data-driven reachability framework for linear systems whose disturbances are modeled by probabilistic zonotopes (PZs), combining bounded deterministic and Gaussian stochastic components. In contrast to methods that require a precisely known disturbance model (either purely deterministic or purely stochastic), we assume only a conservative prior PZ and refine it from data. The framework separates two uncertainty sources: realized disturbances, which act along the collected trajectory and govern the size of the data-consistent model set, and aleatory disturbances, which enter as future additive uncertainty during reachable-set propagation; both shape the reachable sets, but through different mechanisms. Refinement exploits prior system knowledge together with trajectory-consistency constraints induced by the data, which impose affine couplings between deterministic and Gaussian latent variables. We accordingly develop a constrained-PZ calculus that absorbs the stochastic part of these constraints into an equivalent representation, removes infeasible latent directions, and reduces stochastic covariance, together with identification-aware fusion rules for combining heterogeneous constrained-PZ descriptions. The refined realized-disturbance proxies then serve as scenarios in a linear program that learns the smallest translated and scaled copy of the prior disturbance set that contains all proxy confidence sets while remaining nested in the prior. The resulting deterministic, high-probability reachable sets carry formal containment guarantees with substantially reduced conservatism, and numerical examples confirm that the pipeline tightens both the data-consistent model set and the propagated reachable sets.

eess.SY↗
arXiv2026

Perturbation Effects on Robustness and Individual Fairness

Deep neural networks are vulnerable to adversarial perturbations that can simultaneously degrade prediction robustness and individual fairness across diverse application settings. However, existing evaluation protocols typically assess these dimensions in isolation, thereby obscuring critical failure modes. To bridge this gap, we formalize Robust Individual Fairness (RIF): under semantic-preserving (truth-condition-preserving) perturbations, predictions should remain both correct with respect to the ground truth and invariant across semantically equivalent individuals. To surface RIF violations in practice, we introduce RIFair, a black-box adversarial framework that leverages a decoupled perturbation strategy to construct semantically preserved yet unrobust and/or unfair instance pairs. Experiments across multiple model architectures and real-world textual datasets show that robustness-only or fairness-only metrics often miss Robust Biased and Unrobust Fair behaviors. RIFair}reliably exposes these hidden vulnerabilities, supporting RIF as a necessary criterion for trustworthy model assessment. The experimental code is publicly available at https://github.com/Xuran-LI/RIFair.

cs.LG↗
arXiv2026

MAPE: Defending Against Transferable Adversarial Attacks Using Multi-Source Adversarial Perturbations Elimination

Neural networks are vulnerable to meticulously crafted adversarial examples, leading to high-confidence misclassifications in image classification tasks. Due to their consistency with regular input patterns and the absence of reliance on the target model and its output information, transferable adversarial attacks exhibit a notably high stealthiness and detection difficulty, making them a significant focus of defense. In this work, we propose a deep learning defense known as multi-source adversarial perturbations elimination (MAPE) to counter diverse transferable attacks. MAPE comprises the single-source adversarial perturbation elimination (SAPE) mechanism and the pre-trained models probabilistic scheduling algorithm (PPSA). SAPE utilizes a thoughtfully designed channel-attention U-Net as the defense model and employs adversarial examples generated by a pre-trained model (e.g., ResNet) for its training, thereby enabling the elimination of known adversarial perturbations. PPSA introduces model difference quantification and negative momentum to strategically schedule multiple pre-trained models, thereby maximizing the differences among adversarial examples during the defense model's training and enhancing its robustness in eliminating adversarial perturbations. MAPE effectively eliminates adversarial perturbations in various adversarial examples, providing a robust defense against attacks from different substitute models. In a black-box attack scenario utilizing ResNet-34 as the target model, our approach achieves average defense rates of over 95.1\% on CIFAR-10 and over 71.5\% on Mini-ImageNet, demonstrating state-of-the-art performance.

cs.CV↗
arXiv2026

Efficient and Trainable Language Model Test-Time Scaling via Local Branch Routing

Test-time scaling improves language-model reasoning, but existing approaches often face a difficult trade-off: long chain-of-thought sampling remains single-threaded, while sentence- or solution-level search can be computationally expensive and hard to train end-to-end. We introduce Local Branch Routing (LBR), a token-level test-time scaling framework that expands a small local lookahead tree, forwards all sampled branches through the language model, and uses a lightweight router to select the depth-1 subtree to commit. By routing over the hidden states of candidate local futures, LBR allows each token decision to use evidence beyond the root next-token distribution while avoiding full solution-level search. The resulting prune-shift-grow decoding process preserves discrete branch identities and defines a tractable tree-trajectory likelihood: newly grown nodes are counted when first sampled, and router decisions are assigned explicit probabilities. This enables end-to-end reinforcement learning with verifiable rewards, jointly optimizing the base model and router under the same likelihood-ratio principle as discrete-token RLVR. On synthetic hierarchical-planning tasks, LBR shows that post-candidate hidden states provide useful routing evidence. On mathematical reasoning benchmarks, LBR improves both Pass@1 and Pass@32 over discrete chain-of-thought, vanilla discrete-token RLVR, and RL-compatible soft-token branching baselines. These results suggest that lightweight local branching offers an efficient, trainable, and discrete form of language-model test-time scaling.

cs.CL↗
arXiv2026

M-EPDet: Real-Time Real-Bogus Classification and Transient Candidate Judgement for the EP-WXT Pipeline via Multi-Modal Data

The Wide-field X-ray Telescope (WXT) onboard the Einstein Probe (EP) produces a large post-detection candidate stream in which genuine astrophysical sources coexist with instrumental artifacts and Cosmic Ray events. We present M-EPDet, a three-step post-detection framework for real-time candidate vetting in EP-WXT lobster-eye Micro-pore Optics (MPO) data. The framework combines a ResNet-based Arm filter, a dual-branch temporal-spectral Cosmic Ray filter, and a background-aware Bayesian Blocks module for single-exposure variability screening. Using on-orbit EP-WXT observations, we report decoupled metrics for the cascading system. M-EPDet achieves a Real-Bogus Recall of 98.31\% ($98.53\% \times 99.78\%$) for genuine astrophysical sources, together with rejection rates of 92.99\% for instrumental artifacts and 98.18\% for Cosmic Ray events. In the final step, the Bayesian Blocks module flags 0.75\% of the post-filtration observations, corresponding to a 99.25\% reduction in candidate volume. The system is deployed in the EP-WXT pipeline as a lightweight real-time service, reducing the manual-inspection burden in candidate vetting.

astro-ph.IM↗
arXiv2026

MVG-KAN: Multi-View Geo-Wind Guided KAN for PM$_{2.5}$ Forecasting

Accurate short-term PM$_{2.5}$ forecasting is important for public health protection, air-quality early warning, and urban environmental management. However, PM$_{2.5}$ variation is driven by multiple coupled factors, including stable periodic changes induced by human activities and meteorological regularity, station-specific short-term concentration evolution, and meteorology-driven pollutant dispersion among monitoring stations. Existing spatio-temporal forecasting methods may capture station relationships to some extent, but distance-only, correlation-based, or purely adaptive graphs are often insufficient to comprehensively represent these heterogeneous factors, especially wind-direction-dependent pollutant transport. To address this problem, we propose a Multi-View Geo-Wind Guided KAN model for PM$_{2.5}$ forecasting, named \textbf{MVG-KAN}, which models station-level PM$_{2.5}$ evolution from three complementary views: local periodic regularity, station-wise residual temporal dynamics, and meteorological-environment-guided spatial dispersion. Specifically, the periodic-residual forecasting backbone first separates stable daily and weekly patterns from non-periodic residual variations. A Geo-Wind Graph is constructed by combining geographic distance decay with wind-direction- and wind-speed-aware transport, providing a lightweight physically motivated directed spatial prior for residual propagation among stations. In addition, a temporal Kolmogorov-Arnold network (TKAN) residual head is then introduced to learn station-wise nonlinear autoregressive correction from de-periodized PM$_{2.5}$ residuals and historical multi-pollutant sequences, thereby enhancing the modeling of local residual inertia and pollutant co-variation.

cs.AI↗
arXiv2026

A note on simple-minded systems and weakly simple-minded systems over self-injective algebras

Let A be a self-injective algebra over an algebraically closed field. We study the relationship between simple-minded systems and weakly simple-minded systems in A-stmod. We present a necessary and sufficient condition for an orthogonal system to be a simple-minded system over domestic Brauer graph algebras. As a byproduct, we construct a class of simple-minded systems over 2-domestic Brauer graph algebras.

math.RT↗
arXiv2026

A relativistic mechanism for the enhanced isovector spin-orbit interaction suggested by parity-violating electron scattering experiments

Recent high-precision parity-violating electron scattering (PVES) measurements on $^{208}$Pb (PREX-II) and $^{48}$Ca (CREX) reveal a tension in their simultaneous description within modern nuclear energy density functionals (EDFs). Analyses of these data suggest that an enhanced isovector spin-orbit interaction may help account for both measurements, but its relativistic origin in covariant density functional theory remains to be clarified. We show that, within the framework of a covariant density-dependent point-coupling EDF, an enhanced isovector tensor coupling can naturally induce such a strong isovector spin-orbit interaction. This mechanism provides a promising route toward a simultaneous description of the PREX-II and CREX results while preserving a reasonable description of finite nuclei and nuclear matter. PVES on $^{48}$Ca thus provides a sensitive probe of the covariant isovector tensor interaction.

nucl-th↗
arXiv2026

Questioning the Coverage-Length Metric in Conformal Prediction: When Shorter Intervals Are Not Better

Conformal prediction(CP) has become a cornerstone of distribution-free uncertainty quantification, conventionally evaluated by its coverage and interval length. This work critically examines the sufficiency of these standard metrics. We demonstrate that the interval length might be deceptively improved through a counter-intuitive approach termed Prejudicial Trick(PT), while the coverage remains valid. Specifically, for any given test sample, PT probabilistically returns an interval, which is either null or constructed using an adjusted confidence level, thereby preserving marginal coverage. While PT potentially yields a deceptively lower interval length, it introduces practical vulnerabilities: the same input can yield completely different prediction intervals across repeated runs of the algorithm. We formally derive the conditions under which PT achieves these misleading improvements and provide extensive empirical evidence across various regression and classification tasks. Furthermore, we introduce a new metric interval stability which helps detect whether a new CP method implicitly improves the length based on such PT-like techniques. Code is available at https://github.com/benben-cd/PT-Conformal-Prediction.

stat.ML↗
arXiv2026

On reduction and gluing technique of simple-minded systems over self-injective algebras

Let A be a self-injective algebra over an algebraically closed field. We study reduction of simple-minded systems over stable module category A-stmod. We present a recollement and study gluing technique of simple-minded systems through a subset of a simple-minded system in A-stmod. As a byproduct, we also study the extendible property of simple-minded systems.

math.RT↗
arXiv2026

Toward Self-Evolution-Ready Workflow Harnesses: A Reversible Migration Path and Convertibility Taxonomy for Expert LLM Pipelines

While expert-validated "LLM + script" workflows deliver significant value, they remain static: they encode hard-won domain knowledge yet fail to adapt execution based on feedback. Existing agent research predominantly targets greenfield agents and synthetic benchmarks, leaving the migration of active legacy workflows unresolved. To bridge this gap, we present a reversible, Strangler-Fig migration path that refactors legacy workflows into composable, typed, and auditable stages. Central to this framework is a three-tier convertibility taxonomy (A/B/C), implemented as a routing stage within the system harness, which diagnoses a workflow's readiness and routes it accordingly.

cs.SE↗
arXiv2026

Lattice dynamics and the spectroscopic signatures of H-bond disorder in $δ$-AlOOH

Raman and infrared anomalies associated with H-bond symmetrization in $δ$-AlOOH, including mode softening and linewidth broadening at 5-10 GPa, occur at significantly lower pressures than predicted by static harmonic theory. To resolve this discrepancy, we combine harmonic phonon calculations with strongly constrained and appropriately normed (SCAN)-based deep-potential molecular dynamics and phonon quasiparticle analysis at 300 K. This framework extracts temperature- and pressure-dependent frequencies and lifetimes from long-time trajectories, capturing the branch reorganization and rapid linewidth growth characteristic of the disordering regime. Incorporating quasiparticle renormalization and directional longitudinal-optical-transverse-optical (LO-TO) splitting further yields near-quantitative agreement with the ambient-pressure OH-stretching Raman multiplet. These results identify finite-temperature dynamical effects and the progressive loss of spectral coherence as the origin of the spectroscopic signatures of H-bond symmetrization.

cond-mat.mtrl-sci↗
arXiv2026

Deterministic-Allocation and Anonymous Joint Advertising in E-commerce Platforms

With the advancement of machine learning, an increasing number of studies are employing automated mechanism design (AMD) methods for optimal auction design. However, all previous AMD architectures designed to generate optimal mechanisms that satisfy near dominant strategy incentive compatibility (DSIC) fail to achieve deterministic allocation, and some also lack anonymity, thereby impacting the efficiency and fairness of advertising allocation. This has resulted in a notable discrepancy between the previous AMD architectures for generating near-DSIC optimal mechanisms and the demands of real-world advertising scenarios. In this paper, we prove that in all online advertising scenarios, when all ad slots must be allocated, previous non-deterministic allocation AMD methods lead to the non-existence of feasible solutions in the vast majority of cases, resulting in a gap between the rounded solution and the optimal solution. Furthermore, we propose JTransNet, a transformer-based neural network architecture, designed for optimal deterministic-allocation and anonymous joint auction design. Although the deterministic allocation module in JTransNet is designed for the latest joint auction scenarios, it can be applied to other non-deterministic AMD architectures with minor modifications. Additionally, our offline and online data experiments demonstrate that, in joint auction scenarios, JTransNet significantly outperforms the considered baselines in terms of platform revenue.

cs.GT↗
arXiv2026

IAPO: Input Attribution-Aware Policy Optimization for Tool Use in Small Multimodal Agents

This paper investigates reinforcement learning (RL) methods for improving tool-calling capabilities in multimodal small language model (SLM) agents. While existing works have explored various reward designs to improve agentic tool-calling ability, these approaches face inherent limitations for SLM training, especially under multimodal scenarios. First, many existing methods evaluate tool use correctness through exact matching against certain ground-truth or predefined formats. However, this assumption is often unsuitable for multimodal tasks, where multiple tool use paths may be valid and annotated tool trajectories are typically unavailable. Second, such sparse and brittle binary rewards provide little guidance on how to improve the underlying decision process, making them particularly difficult for multimodal SLM to learn from. To address these issues, we propose Input Attribution-Aware Policy Optimization (IAPO), an RL algorithm for improving tool use in multimodal SLM by aligning the model's attribution across input components with that of a stronger teacher. Experiments on Qwen2.5-VL-3B show that the proposed method improves visual question answering accuracy by an average of 3% across six test sets compared with existing visual tool use work, by helping the model attend to the most relevant input evidence.

cs.LG↗