AutoML 2023

24 papers

Meta-Learning for Fast Model Recommendation in Unsupervised Multivariate Time Series Anomaly Detection

Jose Manuel Navarro, Alexis Huet, Dario Rossi

Multi-Predict: Few Shot Predictors For Efficient Neural Architecture Search

Yash Akhauri, Mohamed S Abdelfattah

AlphaD3M: An Open-Source AutoML Library for Multiple ML Tasks

Roque Lopez, Raoni Lourenco, Remi Rampin, Sonia Castelo, Aécio S. R. Santos

Cost-Effective Hyperparameter Optimization for Large Language Model Generation Inference

Chi Wang, Xueqing Liu, Ahmed Hassan Awadallah

Neural Architecture Search for Visual Anomaly Segmentation

Tommie Kerssies, Joaquin Vanschoren

ABLATOR: Robust Horizontal-Scaling of Machine Learning Ablation Experiments

Iordanis Fostiropoulos, Laurent Itti

Exploiting Network Compressibility and Topology in Zero-Cost NAS

Lichuan Xiang, Rosco Hunter, Minghao Xu, Łukasz Dudziak, Hongkai Wen

Searching for Fairer Machine Learning Ensembles

Michael Feffer, Martin Hirzel, Samuel C Hoffman, Kiran Kate, Parikshit Ram

Learning Activation Functions for Sparse Neural Networks

Mohammad Loni, Aditya Mohan, Mehdi Asadi, Marius Lindauer

Computationally Efficient High-Dimensional Bayesian Optimization via Variable Selection

Yihang Shen, Carl Kingsford

“No Free Lunch” in Neural Architectures? A Joint Analysis of Expressivity, Convergence, and Generalization

Wuyang Chen, Wei Huang, Zhangyang Wang

AutoRL Hyperparameter Landscapes

Aditya Mohan, Carolin Benjamins, Konrad Wienecke, Alexander Dockhorn, Marius Lindauer

Optimal Resource Allocation for Early Stopping-based Neural Architecture Search Methods

Marcel Aach, Eray Inanc, Rakesh Sarma, Morris Riedel, Andreas Lintermann

PS-AAS: Portfolio Selection for Automated Algorithm Selection in Black-Box Optimization

Ana Kostovska, Gjorgjina Cenikj, Diederick Vermetten, Anja Jankovic, Ana Nikolikj

Q(D)O-ES: Population-based Quality (Diversity) Optimisation for Post Hoc Ensemble Selection in AutoML

Lennart Oswald Purucker, Lennart Schneider, Marie Anastacio, Joeran Beel, Bernd Bischl

AutoGluon–TimeSeries: AutoML for Probabilistic Time Series Forecasting

Oleksandr Shchur, Ali Caner Turkmen, Nick Erickson, Huibin Shen, Alexander Shirkov

Balanced Mixture of Supernets for Learning the CNN Pooling Architecture

Mehraveh Javan Roshtkhari, Matthew Toews, Marco Pedersoli

MA-BBOB: Many-Affine Combinations of BBOB Functions for Evaluating AutoML Approaches in Noiseless Numerical Black-Box Optimization Contexts

Diederick Vermetten, Furong Ye, Thomas Bäck, Carola Doerr

Self-Adjusting Weighted Expected Improvement for Bayesian Optimization

Carolin Benjamins, Elena Raponi, Anja Jankovic, Carola Doerr, Marius Lindauer

MEOW - Multi-Objective Evolutionary Weapon Detection

Daniel Dimanov, Colin Singleton, Shahin Rostami, Emili Balaguer-Ballester

Better Practices for Domain Adaptation

Linus Ericsson, Da Li, Timothy Hospedales

Poisson Process for Bayesian Optimization

Xiaoxing Wang, Jiaxing Li, Chao Xue, Wei Liu, Weifeng Liu

Symbolic Explanations for Hyperparameter Optimization

Sarah Segel, Helena Graf, Alexander Tornede, Bernd Bischl, Marius Lindauer

CMA-ES for Post Hoc Ensembling in AutoML: A Great Success and Salvageable Failure

Lennart Oswald Purucker, Joeran Beel