arXiv subjects

Chenrui Zhu

Publications and source records attributed to Chenrui Zhu.

3 recordsLinked to original sources

arXiv2026

OPTIMUS-Prime: Minimal and Sufficient Concept Explanations for Deep Vision Models

The growing demand for transparency in automated decision-making has propelled eXplainable Artificial Intelligence (XAI) to the forefront of machine learning research. In computer vision, however, existing explanation methods often prioritize end-user accessibility at the expense of formal guarantees, leaving a critical gap between practical utility and theoretical rigor. In this paper, we address this gap by introducing OPTIMUS, a novel framework for generating concept-based visual explanations for deep classification models. OPTIMUS explanations take the form of visual heatmaps that not only remain interpretable to end users, but are grounded in the well-established theory of prime implicants, providing formal guarantees that have been largely absent from existing saliency-based methods. Specifically, OPTIMUS explanations satisfy two desirable properties: sufficiency, ensuring that the highlighted concepts provably guarantee the classifier's prediction, and minimality, ensuring that no strict subset of those concepts retains this guarantee. Together, these properties yield explanations that are both logically tight and visually coherent. We validate our approach on a visual classification benchmark, demonstrating that OPTIMUS heatmaps naturally and faithfully surface the decision-relevant concepts underlying model predictions.

cs.CV↗

arXiv2025

Robust Explanations Through Uncertainty Decomposition: A Path to Trustworthier AI

Recent advancements in machine learning have emphasized the need for transparency in model predictions, particularly as interpretability diminishes when using increasingly complex architectures. In this paper, we propose leveraging prediction uncertainty as a complementary approach to classical explainability methods. Specifically, we distinguish between aleatoric (data-related) and epistemic (model-related) uncertainty to guide the selection of appropriate explanations. Epistemic uncertainty serves as a rejection criterion for unreliable explanations and, in itself, provides insight into insufficient training (a new form of explanation). Aleatoric uncertainty informs the choice between feature-importance explanations and counterfactual explanations. This leverages a framework of explainability methods driven by uncertainty quantification and disentanglement. Our experiments demonstrate the impact of this uncertainty-aware approach on the robustness and attainability of explanations in both traditional machine learning and deep learning scenarios.

cs.LG↗

arXiv2021

Thermodynamics of black hole in $D$-dimensional $f(R)$ theory

We consider whether the new horizon-first law works in higher-dimensional $f(R)$ theory. We firstly obtain the general formulas to calculate the entropy and the energy of a general spherically-symmetric black hole in $D$-dimensional $f(R)$ theory. For applications, we compute the entropies and the energies of some black hokes in some interesting higher-dimensional $f(R)$ theories.

gr-qc↗