Criticality and universality in network dismantling
研究通过引入自适应偏置渗流过程,解决网络拆解过程中结构连通性受节点或边移除影响的问题,发现该过程在不同度分布的网络中表现出普遍相变。
研究通过引入自适应偏置渗流过程,解决网络拆解过程中结构连通性受节点或边移除影响的问题,发现该过程在不同度分布的网络中表现出普遍相变。
研究了难优化问题算法缓慢收敛于平凡解的问题,通过分析和实验表明,在有限规模下,局部算法表现优于理论预测。
This study investigates the open-ended innovation dynamics in zero-sum games driven by both players continuously introducing novel strategies. Modeling innovation as the sampling of new strategies from a strategy distribution, the work integrates game-theoretic and probabilistic methods to analyze how one player’s technological advancement increases the marginal returns for the opponent’s further innovation. Theoretically, under general conditions, this adversarial interaction inevitably triggers an unending innovation arms race, resulting in a perpetual cycle of strategic evolution. The analysis thus reveals an endogenous mechanism that sustains open-ended innovation in competitive environments, demonstrating that strategic interdependence alone can perpetuate continuous adaptation without external stimuli.
This work investigates the information-theoretic limits of learning from a hierarchical single-hidden-layer teacher network and transferring knowledge to a smaller student model in high-dimensional, noisy settings. Leveraging tools from high-dimensional statistical physics, leave-one-out decoupling, and fixed-point equation analysis, the study reveals a sequence of sharp phase transitions in feature learning: as the sample size increases, features at different hierarchical levels become learnable successively. The authors introduce the notion of “effective width,” which unifies two previously known scaling laws and yields a closed-form expression for the Bayes-optimal generalization error, scaling as Θ(k_c d/n). Experiments demonstrate that training student models near this effective width enables them to closely approach the theoretical performance limit.
Existing XAI methods exhibit insufficient reliability and trustworthiness for minority-class predictions in imbalanced datasets—particularly critical in high-stakes domains. Method: We propose the first XAI robustness evaluation framework specifically designed for minority classes. It constructs semantic neighborhoods grounded in manifold structure, then quantifies explanation stability via explanation aggregation and consistency measurement. Contribution/Results: By integrating manifold learning with XAI evaluation—departing from conventional uniform sampling assumptions—the framework significantly improves interpretability fidelity for rare events (e.g., frost detection). Experiments on multiple imbalanced tabular datasets demonstrate its effectiveness in identifying fragile explanations, substantially enhancing both the explainability of minority-class predictions and the reliability of downstream decisions.
研究通过引入自适应偏置渗流过程,解决网络拆解过程中结构连通性受节点或边移除影响的问题,发现该过程在不同度分布的网络中表现出普遍相变。
研究了难优化问题算法缓慢收敛于平凡解的问题,通过分析和实验表明,在有限规模下,局部算法表现优于理论预测。
This study investigates the open-ended innovation dynamics in zero-sum games driven by both players continuously introducing novel strategies. Modeling innovation as the sampling of new strategies from a strategy distribution, the work integrates game-theoretic and probabilistic methods to analyze how one player’s technological advancement increases the marginal returns for the opponent’s further innovation. Theoretically, under general conditions, this adversarial interaction inevitably triggers an unending innovation arms race, resulting in a perpetual cycle of strategic evolution. The analysis thus reveals an endogenous mechanism that sustains open-ended innovation in competitive environments, demonstrating that strategic interdependence alone can perpetuate continuous adaptation without external stimuli.
This work investigates the information-theoretic limits of learning from a hierarchical single-hidden-layer teacher network and transferring knowledge to a smaller student model in high-dimensional, noisy settings. Leveraging tools from high-dimensional statistical physics, leave-one-out decoupling, and fixed-point equation analysis, the study reveals a sequence of sharp phase transitions in feature learning: as the sample size increases, features at different hierarchical levels become learnable successively. The authors introduce the notion of “effective width,” which unifies two previously known scaling laws and yields a closed-form expression for the Bayes-optimal generalization error, scaling as Θ(k_c d/n). Experiments demonstrate that training student models near this effective width enables them to closely approach the theoretical performance limit.
Existing XAI methods exhibit insufficient reliability and trustworthiness for minority-class predictions in imbalanced datasets—particularly critical in high-stakes domains. Method: We propose the first XAI robustness evaluation framework specifically designed for minority classes. It constructs semantic neighborhoods grounded in manifold structure, then quantifies explanation stability via explanation aggregation and consistency measurement. Contribution/Results: By integrating manifold learning with XAI evaluation—departing from conventional uniform sampling assumptions—the framework significantly improves interpretability fidelity for rare events (e.g., frost detection). Experiments on multiple imbalanced tabular datasets demonstrate its effectiveness in identifying fragile explanations, substantially enhancing both the explainability of minority-class predictions and the reliability of downstream decisions.