The paper introduces a unified theoretical framework for gradient aggregation in multi-objective optimization, establishing convergence rates and sufficient conditions for achieving Pareto stationarit…

This paper investigates the benefits of generating multiple solutions in each generation for Evolutionary Diversity Optimisation (EDO) and proposes efficient methods to achieve it.

The paper conducts a runtime analysis of the Strength Pareto Evolutionary Algorithm 2 (SPEA2) and proposes an improved variant, SPEA2$^+$, to address its limitations in handling dominated solutions.

ParetoPilot introduces a novel zero-surrogate diffusion framework for offline multi-objective optimization, achieving state-of-the-art performance by directly guiding the generation process without re…

This paper proposes a game-theoretic framework using Shapley Effects and Pareto front sets for interpretable hyperparameter-objective interaction analysis.

This paper provides theoretical analysis of parameter settings for the bat algorithm using dynamical systems and population variance theory, and validates the results through numerical experiments.

The paper analyzes preference-shaped expected improvement criteria for Bayesian multiobjective optimization, precisely characterizing when transformations preserve key properties like exact computatio…

This paper derives an exact Bellman dynamic program for subset selection with a continuous integral $R_2$ indicator using an adjacent-neighbor decomposition.

This paper proposes a Hybrid Augmented Lagrangian (HyAL) method that integrates the constraint-handling strengths of the AL framework with the exploratory power of population-based search.

The paper proposes a novel, theoretically-grounded algorithm (HAMU) that addresses the challenge of machine unlearning by guaranteeing specified improvements in forget quality while minimizing retain…

The paper establishes conditions for QUBO formulations of combinatorial optimization problems that guarantee valid binary and feasible local minimizers using gradient-based methods.

This paper compares the effect of different initialization methods on the accuracy and complexity of solutions in genetic programming for symbolic regression, finding no significant differences.

This paper analyzes the performance and explainability requirements of evolutionary algorithms when applied to complex, real-world physics-informed optimization problems, identifying a gap between cur…

This paper introduces DE-2LS, a late-stage, local-search-enhanced differential evolution framework for unconstrained single-objective optimization with variable bounds.

The paper develops an explicit multi-linear polynomial form for binary polynomial optimization problems after eliminating a subset of variables, allowing for characterization of new special classes wi…