Accepted Papers
Contributed Talks (presented in poster session 2)
Discovering Weight Initializers with Meta Learning
Dmitry Baranchuk and Artem Babenko.
Multimodal AutoML on Structured Tables with Text Fields
Xingjian Shi, Jonas Mueller, Nick Erickson, Mu Li and Alex Smola.
Automated Discovery of Adaptive Attacks on Adversarial Defenses
Chengyuan Yao, Pavol Bielik, Petar Tsankov and Martin Vechev.
Poster Session 1
A resource-efficient method for repeated HPO and NAS problems
Giovanni Zappella, David Salinas and Cedric Archambeau.
Latency-Aware Neural Architecture Search with Multi-Objective Bayesian Optimization
David Eriksson, Pierce I-Jen Chuang, Samuel Daulton, Peng Xia, Akshat Shrivastava, Arun Babu, Shicong Zhao, Ahmed A Aly, Ganesh Venkatesh and Maximilian Balandat.
GPy-ABCD: A Configurable Automatic Bayesian Covariance Discovery Implementation
Thomas Fletcher, Alan Bundy and Kwabena Nuamah.
Bandit Limited Discrepancy Search and Application to Machine Learning Pipeline Optimization
Akihiro Kishimoto, Djallel Bouneffouf, Radu Marinescu, Parikshit Ram, Ambrish Rawat, Martin Wistuba, Paulito Pedregosa Palmes and Adi Botea.
Towards Model Selection using Learning Curve Cross-Validation
Felix Mohr and Jan N. van Rijn.
Dynamic Pruning of a Neural Network via Gradient Signal-to-Noise Ratio
Julien Niklas Siems, Aaron Klein, Cedric Archambeau and Maren Mahsereci.
AutoML Adoption in ML Software
Koen Van der Blom, Alex Serban, Holger Hoos and Joost Visser.
Leveraging Theoretical Tradeoffs in Hyperparameter Selection for Improved Empirical Performance
Parikshit Ram, Alexander G. Gray and Horst Samulowitz.
Bag of Baselines for Multi-objective Joint Neural Architecture Search and Hyperparameter Optimization
Thomas Elsken, Julia Guerrero-Viu, Sven Hauns, Sergio Izquierdo, Simon Schrodi, André Biedenkapp, Difan Deng, Marius Lindauer, Frank Hutter and Guilherme Miotto.
Towards Explaining Hyperparameter Optimization via Partial Dependence Plots
Julia Moosbauer, Julia Herbinger, Giuseppe Casalicchio, Marius Lindauer and Bernd Bischl.
Mutation is all you need
Lennart Schneider, Florian Pfisterer, Martin Binder and Bernd Bischl.
Meta Learning the Step Size in Policy Gradient Methods
Luca Sabbioni, Francesco Corda and Marcello Restelli.
Poster Session 2
Sequential Automated Machine Learning: Bandits-driven Exploration using a Collaborative Filtering Representation
Maxime Heuillet, Benoit Debaque and Audrey Durand.
LRTuner: A Learning Rate Tuner for Deep Neural Networks
Nikhil Iyer, Thejas Venkatesh, Nipun Kwatra, Ramachandran Ramjee and Muthian Sivathanu.
PonderNet: Learning to Ponder
Andrea Banino, Jan Balaguer and Charles Blundell.
PDF Poster (not yet available)
Replacing the Ex-Def Baseline in AutoML by Naive AutoML
Felix Mohr and Marcel Wever.
Neural Fixed-Point Acceleration for Convex Optimization
Shobha Venkataraman and Brandon Amos.
Ranking Architectures by Feature Extraction Capabilities
Debadeepta Dey, Shital Shah and Sebastien Bubeck.
Incorporating domain knowledge into neural-guided search via in situ priors and constraints
Brenden K Petersen, Claudio Santiago and Mikel Landajuela.
Tabular Data: Deep Learning is Not All You Need
Ravid Shwartz-Ziv and Amitai Armon.
Automated Learning Rate Scheduler for Large-batch Training
Chiheon Kim, Saehoon Kim, Jongmin Kim, Donghoon Lee and Sungwoong Kim.
Adaptation-Agnostic Meta-Training
Jiaxin Chen, Li-Ming Zhan, Xiao-Ming Wu and Fu-lai Chung.
On-the-fly learning of adaptive strategies with bandit algorithms
Rashid Bakirov, Damien Fay and Bogdan Gabrys.