paper-with-me

홈 › Papers

Procrastinating with Confidence: Near-Optimal, Anytime, Adaptive Algorithm Configuration

2019-02-14 · NeurIPS 2019 12 · Robert Kleinberg, Kevin Leyton-Brown, Brendan Lucier, Devon Graham

Algorithm configuration methods optimize the performance of a parameterized heuristic algorithm on a given distribution of problem instances. Recent work introduced an algorithm configuration procedure ("Structured Procrastination") that provably achieves near optimal performance with high probability and with nearly minimal runtime in the worst case. It also offers an $\textit{anytime}$ property: it keeps tightening its optimality guarantees the longer it is run. Unfortunately, Structured Procrastination is not $\textit{adaptive}$ to characteristics of the parameterized algorithm: it treats every input like the worst case. Follow-up work ("LeapsAndBounds") achieves adaptivity but trades away the anytime property. This paper introduces a new algorithm, "Structured Procrastination with Confidence", that preserves the near-optimality and anytime properties of Structured Procrastination while adding adaptivity. In particular, the new algorithm will perform dramatically faster in settings where many algorithm configurations perform poorly. We show empirically both that such settings arise frequently in practice and that the anytime property is useful for finding good configurations quickly.

📄 PDF Abstract BibTeX arXiv:1902.05454

Code (1)

drgrhm/alg_config 공식 구현

Similar Papers 제목 키워드 기반

Nonmyopic Gaussian Process Optimization with Macro-Actions

2020-02-22 · Dmitrii Kharkovskii, Chun Kai Ling, Kian Hsiang Low

This paper presents a multi-staged approach to nonmyopic adaptive Gaussian process optimization (GPO) for Bayesian optimization (BO) of unknown, highly complex objective functions that, in contrast to existing nonmyopic …

Bayesian Optimization

GAAVI: Global Asymptotic Anytime Valid Inference for the Conditional Mean Function

2026-02-08 · Brian M Cho, Raaz Dwivedi, Nathan Kallus arxiv

Inference on the conditional mean function (CMF) is central to tasks from adaptive experimentation to optimal treatment assignment and algorithmic fairness auditing. In this work, we provide a novel asymptotic anytime-va…

Bandits with Anytime Knapsacks

2025-01-30 · Eray Can Elumar, Cem Tekin, Osman Yagan

We consider bandits with anytime knapsacks (BwAK), a novel version of the BwK problem where there is an \textit{anytime} cost constraint instead of a total cost budget. This problem setting introduces additional complexi…

Decision Making

Learning Anytime Predictions in Neural Networks via Adaptive Loss Balancing

2017-08-22 · Hanzhang Hu, Debadeepta Dey, Martial Hebert, J. Andrew Bagnell

This work considers the trade-off between accuracy and test-time computational cost of deep neural networks (DNNs) via \emph{anytime} predictions from auxiliary predictions. Specifically, we optimize auxiliary losses joi…

Anytime Dense Prediction with Confidence Adaptivity

2021-04-01 · ICLR 2022 4 · Zhuang Liu, Zhiqiu Xu, Hung-Ju Wang, Trevor Darrell 외

Anytime inference requires a model to make a progression of predictions which might be halted at any time. Prior research on anytime visual recognition has mostly focused on image classification. We propose the first uni…

image-classificationImage ClassificationPose EstimationPrediction+1