This paper introduces Curvature-Weighted Gradient Diversity (CWGD), a geometry-aware measure for optimization noise that reduces the asymptotic optimization error floor by up to a factor of two compar…

This paper proposes HT-PAder, a parameter-free algorithm for online convex optimization in non-stationary environments with heavy-tailed noise, achieving an expected universal dynamic regret.

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

The paper introduces Singularity-aware Adam (S-Adam), a novel optimizer that stabilizes deep learning training in non-smooth loss landscapes by dynamically damping updates based on local geometric ins…

The authors compare and evaluate 20 software configuration optimizers based on six assumptions about the data, and find that no single optimizer outperforms others across all budgets. They propose a t…

The paper proposes FOAM, an adaptive damping method that stabilizes the Shampoo optimization algorithm by dynamically controlling damping and eigendecomposition frequency, thereby reducing staleness-i…

This paper shows that stochastic nonconvex optimization can be reduced to ordinary static regret minimization in online convex optimization, and establishes convergence rates for smooth and Lipschitz…

KLineage introduces a novel method to teach LLMs when and how to apply GPU kernel optimizations by reverse-engineering expert kernel lineages, resulting in superior optimization skills compared to exi…

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 proposes using pseudo-sensitivities, derived from adjoint sensitivity fields, as an optimal conditioning signal in a Bernoulli flow-matching framework to significantly improve the out-of-dis…

The paper introduces Opt-Verifier, a novel LLM-based framework that significantly improves the accuracy of automated optimization model generation by implementing dual-side verification from both stru…

This paper introduces a novel class of backdoor attacks that exploit the numerical side effects of LLM inference optimization, achieving high success rates while maintaining clean accuracy.

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

This paper derives the complete theory of covariance regret functional for decision making, providing insights on steepest-descent directions and boundary-optimal solutions.

This paper introduces Neural Certificate Pricing (NCP), an unsupervised learning framework that exploits the asymmetry between certifiable discrete structures and structural feasibility in combinatori…

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

This paper proves the conjecture that Local SGD outperforms Mini-batch SGD under bounded second-order heterogeneity for general convex objectives, improving the convergence guarantee and lower bounds.

This paper measures the lower bound for the shortest program generating a sequence, proving a conservation law and providing a deterministic engine to recover generating programs for certain sequences…