paper-with-me

홈 › Papers

Improved Fixed-Budget Results via Drift Analysis

2020-06-12 · Timo Kötzing, Carsten Witt

Fixed-budget theory is concerned with computing or bounding the fitness value achievable by randomized search heuristics within a given budget of fitness function evaluations. Despite recent progress in fixed-budget theory, there is a lack of general tools to derive such results. We transfer drift theory, the key tool to derive expected optimization times, to the fixed-budged perspective. A first and easy-to-use statement concerned with iterating drift in so-called greed-admitting scenarios immediately translates into bounds on the expected function value. Afterwards, we consider a more general tool based on the well-known variable drift theorem. Applications of this technique to the LeadingOnes benchmark function yield statements that are more precise than the previous state of the art.

📄 PDF Abstract BibTeX arXiv:2006.07019

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Learning under Distributional Drift: Prequential Reproducibility as an Intrinsic Statistical Resource

2025-12-15 · Sofiya Zaichyk arxiv

Statistical learning under distributional drift remains poorly characterized, especially in closed-loop settings where learning alters the data-generating law. We introduce an intrinsic drift budget $C_T$ that quantifies…

Optimize Wider, Not Deeper: Consensus Aggregation for Policy Optimization

2026-03-13 · Zelal Su, Mustafaoglu, Sungyoung Lee, Eshan Balachandar 외 arxiv

Proximal policy optimization (PPO) approximates the trust region update using multiple epochs of clipped SGD. Each epoch may drift further from the natural gradient direction, creating path-dependent noise. To understand…

Continuous Control

WHERE to Generate Matters: Budget-Aware Synthetic Augmentation for Label Skewed Federated Learning

2026-07-07 · Sangwoo Lee, Sunghwan Park, Jaewoo Lee arxiv

Label skew in federated learning (FL) causes client drift and degrades global accuracy. Synthetic data augmentation can reduce this imbalance; however, full class balancing requires substantial computation cost. We propo…

Federated LearningData Augmentation

Unlimited Budget Analysis of Randomised Search Heuristics

2019-09-07 · Jun He, Thomas Jansen, Christine Zarges

Performance analysis of all kinds of randomised search heuristics is a rapidly growing and developing field. Run time and solution quality are two popular measures of the performance of these algorithms. The focus of thi…

Objective Matters: Fine-Tuning Objectives Shape Safety, Robustness, and Persona Drift

2026-01-19 · Daniel Vennemeyer, Punya Syon Pandey, Phan Anh Duong, Michael Umeokoli 외 arxiv

Fine-tuning LLMs on benign data can still degrade alignment and adversarial robustness, yet direct analysis of the role of fine-tuning objectives in shaping these safety outcomes remain limited. We present a controlled c…

Adversarial Robustness