Institution profile

Abdus Salam International Centre for Theoretical Physics

Academic institutioneurope · it
Official website
Research library6linked papers
Opportunities0open roles
Selected work

Representative Papers

Open-ended innovation in zero-sum games

Jul 28, 2026

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.

0 citationsRead paper

Sharp feature-learning transitions and Bayes-optimal neural scaling laws in extensive-width networks

May 11, 2026

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.

0 citationsRead paper

Assessing reliability of explanations in unbalanced datasets: a use-case on the occurrence of frost events

Jul 13, 2025

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.

0 citationsRead paper
Recent publications

Latest Papers

Open-ended innovation in zero-sum games

Jul 28, 2026

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.

0 citationsRead paper

Sharp feature-learning transitions and Bayes-optimal neural scaling laws in extensive-width networks

May 11, 2026

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.

0 citationsRead paper

Assessing reliability of explanations in unbalanced datasets: a use-case on the occurrence of frost events

Jul 13, 2025

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.

0 citationsRead paper