paper-with-me

Papers

Automated Hyperparameter Optimization Challenge at CIKM 2021 AnalyticCup

2021-10-31 · Huaijun Jiang, Yu Shen, Yang Li

In this paper, we describe our method for tackling the automated hyperparameter optimization challenge in QQ Browser 2021 AI Algorithm Competiton (ACM CIKM 2021 AnalyticCup Track 2). The competition organizers provide anonymized realistic industrial tasks and datasets for black-box optimization. Based on our open-sourced package OpenBox, we adopt the Bayesian optimization framework for configuration sampling and a heuristic early stopping strategy. We won first place in both the preliminary and final contests with the results of 0.938291 and 0.918753, respectively.

📄 PDF Abstract BibTeX arXiv:2111.00513

Code (1)

PKU-DAIR/open-box 공식 구현

Tasks

Bayesian OptimizationHyperparameter Optimization

Methods 이 논문이 사용한 방법론

Early Stopping Early Stopping is a regularization technique for deep neural networks that stops training when parameter updates no longer begin to yield improves on a validation set. In…

Similar Papers 제목 키워드 기반

CIKMar: A Dual-Encoder Approach to Prompt-Based Reranking in Educational Dialogue Systems

2024-08-16 · Joanito Agili Lopo, Marina Indah Prasasti, Alma Permatasari

In this study, we introduce CIKMar, an efficient approach to educational dialogue systems powered by the Gemma Language model. By leveraging a Dual-Encoder ranking system that incorporates both BERT and SBERT model, we h…

Language ModelingLanguage ModellingReranking

Cross Device Matching for Online Advertising with Neural Feature Ensembles : First Place Solution at CIKM Cup 2016

2016-10-23 · Minh C. Phan, Yi Tay, Tuan-Anh Nguyen Pham

We describe the 1st place winning approach for the CIKM Cup 2016 Challenge. In this paper, we provide an approach to reasonably identify same users across multiple devices based on browsing logs. Our approach regards a c…

ClassificationGeneral Classification

Hyperparameter Importance Across Datasets

2017-10-12 · J. N. van Rijn, F. Hutter

With the advent of automated machine learning, automated hyperparameter optimization methods are by now routinely used in data mining. However, this progress is not yet matched by equal progress on automatic analyses tha…

Hyperparameter OptimizationMeta-Learning

Using Generative Adversarial Nets on Atari Games for Feature Extraction in Deep Reinforcement Learning

2020-04-06 · Ayberk Aydın, Elif Surer

Deep Reinforcement Learning (DRL) has been successfully applied in several research domains such as robot navigation and automated video game playing. However, these methods require excessive computation and interaction …

Atari GamesDeep Reinforcement LearningReinforcement LearningRepresentation Learning+1

MANGO: A Python Library for Parallel Hyperparameter Tuning

2020-05-22 · Sandeep Singh Sandha, Mohit Aggarwal, Igor Fedorov, Mani Srivastava

Tuning hyperparameters for machine learning algorithms is a tedious task, one that is typically done manually. To enable automated hyperparameter tuning, recent works have started to use techniques based on Bayesian opti…

Bayesian OptimizationBIG-bench Machine LearningDistributed ComputingDistributed Optimization+2