Fetching the paper…
Reading the bibliography…
Meta-learning, or learning to learn, is the science of systematically observing how different machine learning approaches perform on a wide range of learning tasks, and then learning from this experience, or meta-data, to learn new tasks much faster than otherwise possible.
On the likelihood that one unknown probability exceeds another in view of the evidence of two samples
William R Thompson · 1933
Earlier work this paper cites.
A new measure of rank correlation
Maurice G Kendall · 1938
Earlier work this paper cites.
On information and sufficiency
Solomon Kullback and Richard A Leibler · 1951
Earlier work this paper cites.
On estimating regression
Elizbar A Nadaraya · 1964
Earlier work this paper cites.
Some aspects of the sequential design of experiments
Herbert Robbins · 1985
Earlier work this paper cites.
The evolution of learning: An experiment in genetic connectionism
David J Chalmers · 1991
Earlier work this paper cites.
Learning to control fast-weight memories: An alternative to dynamic recurrent networks
Jürgen Schmidhuber · 1992
Earlier work this paper cites.
A neural network that embeds its own meta-levels
Jürgen Schmidhuber · 1993
Earlier work this paper cites.
Adaptive Generalization
N. E. Sharkey and A. J. C. Sharkey · 1993
Earlier work this paper cites.
Selecting appropriate forecasting models using rule induction
B Arinze · 1994
Earlier work this paper cites.
Machine Learning, Neural and Statistical Classification
Donald Michie, David J. Spiegelhalter, Charles C. Taylor, and John Campbell · 1994
Earlier work this paper cites.
On the search for new learning rules for anns
Samy Bengio, Yoshua Bengio, and Jocelyn Cloutier · 1995
Earlier work this paper cites.
Learning many related tasks at the same time with backpropagation
R. Caruana · 1995
Earlier work this paper cites.
Automatic parameter selection by minimizing estimated error
Ron Kohavi and George H John · 1995
Earlier work this paper cites.
Learning One More Thing
S. Thrun and T. Mitchell · 1995
Earlier work this paper cites.
Learning Internal Representations
J. Baxter · 1996
Earlier work this paper cites.
A general framework for distance-based consensus in ordinal ranking models
W. D. Cook, M. Kress, and L. W. Seiford · 1996
Earlier work this paper cites.
No free lunch theorems for search
D.H. Wolpert and W.G. Macready · 1996
Earlier work this paper cites.
Multitask Learning
R. Caruana · 1997
Earlier work this paper cites.
Long short-term memory
Sepp Hochreiter and Jürgen Schmidhuber · 1997
Earlier work this paper cites.
Shifting inductive bias with success-story algorithm, adaptive levin search, and incremental self-improvement
Jürgen Schmidhuber, Jieyu Zhao, and Marco Wiering · 1997
Earlier work this paper cites.
Efficient global optimization of expensive black-box functions
Donald R Jones, Matthias Schonlau, and William J Welch · 1998
Earlier work this paper cites.
Lifelong Learning Algorithms
S. Thrun · 1998
Earlier work this paper cites.
Learning to Learn: Introduction and Overview
S. Thrun and L. Pratt · 1998
Earlier work this paper cites.
AST: Support for algorithm selection with a CBR approach
G. Lindner and R. Studer · 1999
Earlier work this paper cites.
Efficient progressive sampling
Foster Provost, David Jensen, and Tim Oates · 1999
Earlier work this paper cites.
Experiments in meta-level learning with ILP
L Todorovski and S Dzeroski · 1999
Earlier work this paper cites.
Understanding accuracy performance through concept characterization and algorithm analysis
R Vilalta · 1999
Earlier work this paper cites.
Discovering task neighbourhoods through landmark learning performances
Hilan Bensusan and Christophe Giraud-Carrier · 2000
Earlier work this paper cites.
A higher-order approach to meta-learning
Hilan Bensusan, Christophe Giraud-Carrier, and Claire Kennedy · 2000
Earlier work this paper cites.
Ensemble methods in machine learning
T Dietterich · 2000
Earlier work this paper cites.
Meta-analysis: From data characterization for meta-learning to meta-regression
C. Köpf, C. Taylor, and J. Keller · 2000
Earlier work this paper cites.
Meta-learning by landmarking various learning algorithms
Bernhard Pfahringer, Hilan Bensusan, and Christophe G. Giraud-Carrier · 2000
Earlier work this paper cites.
Evolution and design of distributed learning rules
Thomas Philip Runarsson and Magnus Thor Jonsson · 2000
Earlier work this paper cites.
Report on the experiments with feature selection in meta-level learning
L Todorovski, P Brazdil, and C Soares · 2000
Earlier work this paper cites.
Estimating the predictive accuracy of a classifier
H Bensusan and A Kalousis · 2001
Earlier work this paper cites.
An evaluation of landmarking variants
J Fürnkranz and J Petrak · 2001
Earlier work this paper cites.
Fusion of meta-knowledge and meta-data for case-based model selection
M Hilario and A Kalousis · 2001
Earlier work this paper cites.
Learning to learn using gradient descent
S. Hochreiter, A.S. Younger, and P.R. Conwell · 2001
Earlier work this paper cites.
Model selection via meta-learning: a comparative study
Alexandros Kalousis and Melanie Hilario · 2001
Earlier work this paper cites.
Sampling based relative landmarks: Systematically testdriving algorithms before choosing
C Soares, J Petrak, and P Brazdil · 2001
Earlier work this paper cites.
Categorical Data Analysis
A. Agresti · 2002
Earlier work this paper cites.
Action Refinement in Reinforcement Learning by Probability Smoothing
T. Dietterich, D. Busquets, R. Lopez de Mantaras, and C. Sierra · 2002
Earlier work this paper cites.
Discovering Hierarchy in Reinforcement Learning with HEXQ
B. Hengst · 2002
Earlier work this paper cites.
Complexity measures of supervised classification problems
Tin Kam Ho and Mitra Basu · 2002
Earlier work this paper cites.
Algorithm Selection via Meta-Learning
A. Kalousis · 2002
Earlier work this paper cites.
Combination of task description strategies and case base properties for meta-learning
C Köpf and I Iglezakis · 2002
Earlier work this paper cites.
Exploiting sampling and meta-learning for parameter setting support vector machines
P. Kuba, P. Brazdil, C. Soares, and A. Woznica · 2002
Earlier work this paper cites.
Improved dataset characterisation for meta-learning
Y Peng, P Flach, C Soares, and P Brazdil · 2002
Earlier work this paper cites.
Ranking with predictive clustering trees
L. Todorovski, H. Blockeel, and S. Džeroski · 2002
Earlier work this paper cites.
A characterization of difficult problems in classification
R Vilalta and Y Drissi · 2002
Earlier work this paper cites.
Task Clustering and Gating for Bayesian Multitask Learning
B. Bakker and T. Heskes · 2003
Earlier work this paper cites.
Representational issues in meta-learning
A Kalousis and M Hilario · 2003
Earlier work this paper cites.
Selection of time series forecasting models based on performance information
P dos Santos, T Ludermir, and R Prudêncio · 2004
Earlier work this paper cites.
Regularized multi-task learning
T. Evgeniou and M. Pontil · 2004
Earlier work this paper cites.
Meta-learning approaches to selecting time series models
R Prudêncio and T Ludermir · 2004
Earlier work this paper cites.
Gaussian processes in machine learning
Carl Edward Rasmussen · 2004
Earlier work this paper cites.
A meta-learning method to select the kernel width in support vector regression
C. Soares, P. Brazdil, and P. Kuba · 2004
Earlier work this paper cites.
Cross-generalization: Learning novel classes from a single example by feature replacement
Evgeniy Bart and Shimon Ullman · 2005
Earlier work this paper cites.
Meta-data: Characterization of input features for meta-learning
Ciro Castiello, Giovanna Castellano, and Anna Maria Fanelli · 2005
Earlier work this paper cites.
Learning Multiple Tasks with Kernel Methods
T. Evgeniou, C. Micchelli, and M. Pontil · 2005
Earlier work this paper cites.
Object classification from a single example utilizing class relevance metrics
Michael Fink · 2005
Cited alongside, same era.
Toward a justification of meta-learning: Is the no free lunch theorem a show-stopper
Christophe Giraud-Carrier and Foster Provost · 2005
Cited alongside, same era.
Predicting relative performance of classifiers from samples
R Leite and P Brazdil · 2005
Cited alongside, same era.
Utilizing regression-based landmarkers within a meta-learning framework for algorithm selection
Daren Ler, Irena Koprinska, and Sanjay Chawla · 2005
Cited alongside, same era.
Learning the Structure of Related Tasks
A. Niculescu-Mizil and R. Caruana · 2005
Cited alongside, same era.
To Transfer or Not To Transfer
M. T. Rosenstein, Z. Marx, and L. P. Kaelbling · 2005
Cited alongside, same era.
Hyperparameter search space pruning, a new component for sequential model-based hyperparameter optimization
M. Wistuba, N. Schilling, and L. Schmidt-Thieme · 2015
Later among the works it cites.
Learning to learn by gradient descent by gradient descent
Marcin Andrychowicz, Misha Denil, Sergio Gomez, Matthew W Hoffman, David Pfau, Tom Schaul, Brendan Shillingford, and Nando De Freitas · 2016
Later among the works it cites.
ASLib: A benchmark library for algorithm selection
B. Bischl, P. Kerschke, L. Kotthoff, M. Lindauer, Y. Malitsky, A. Fréchette, H. Hoos, F. Hutter, K. Leyton-Brown, K. Tierney, and J. Vanschoren · 2016
Later among the works it cites.
Learning to learn without gradient descent by gradient descent
Yutian Chen, Matthew W Hoffman, Sergio Gómez Colmenarejo, Misha Denil, Timothy P Lillicrap, Matt Botvinick, and Nando de Freitas · 2016
Later among the works it cites.
Learning step size controllers for robust neural network training
Christian Daniel, Jonathan Taylor, and Sebastian Nowozin · 2016
Later among the works it cites.
alphaXiv searches the wider corpus for related work and actual follow-ups.
alphaXiv is searching for related work…
Pattern recognition and machine learning
Christopher M Bishop · 2006
Cited alongside, same era.
Statistical Comparisons of Classifiers over Multiple Data Sets
J. Demšar · 2006
Cited alongside, same era.
Knowledge transfer in learning to recognize visual objects classes
Li Fei-Fei · 2006
Cited alongside, same era.
One-shot learning of object categories
Li Fei-Fei, Rob Fergus, and Pietro Perona · 2006
Cited alongside, same era.
Transfer Learning by Constructing Informative Priors
R. Raina, A. Y. Ng, and D. Koller · 2006
Cited alongside, same era.
An iterative process for building learning curves and predicting relative performance of classifiers
R Leite and P Brazdil · 2007
Cited alongside, same era.
RL 2 : Fast reinforcement learning via slow reinforcement learning
Yan Duan, John Schulman, Xi Chen, Peter L Bartlett, Ilya Sutskever, and Pieter Abbeel · 2016
Later among the works it cites.
Ke Li and Jitendra Malik · 2016
Later among the works it cites.
A review of automatic selection methods for machine learning algorithms and hyper-parameter values
Gang Luo · 2016
Later among the works it cites.
Hyper-parameter tuning of a decision tree induction algorithm
Rafael G Mantovani, Tomáš Horváth, Ricardo Cerri, Joaquin Vanschoren, and André CPLF de Carvalho · 2016
Later among the works it cites.
Evaluation of a tree-based pipeline optimization tool for automating data science
Randal S Olson, Nathan Bartley, Ryan J Urbanowicz, and Jason H Moore · 2016
Later among the works it cites.
Towards automatic generation of metafeatures
Fábio Pinto, Carlos Soares, and João Mendes-Moreira · 2016
Later among the works it cites.
Does Feature Selection Improve Classification? A Large Scale Experiment in OpenML
Martijn J. Post, Peter van der Putten, and Jan N. van Rijn · 2016
Later among the works it cites.
Bayesian optimization with robust Bayesian neural networks
J. Springenberg, A. Klein, S. Falkner, and Frank Hutter · 2016
Later among the works it cites.
Matching networks for one shot learning
Oriol Vinyals, Charles Blundell, Tim Lillicrap, Daan Wierstra, et al · 2016
Later among the works it cites.
Learning to reinforcement learn
Jane X Wang, Zeb Kurth-Nelson, Dhruva Tirumala, Hubert Soyer, Joel Z Leibo, Remi Munos, Charles Blundell, Dharshan Kumaran, and Matt Botvinick · 2016
Later among the works it cites.
On the predictive power of meta-features in OpenML
Besim Bilalli, Alberto Abelló, and Tomàs Aluja-Banet · 2017
Later among the works it cites.
Speeding up hyper-parameter optimization by extrapolation of learning curves using previous builds
Akshay Chandrashekaran and Ian R Lane · 2017
Later among the works it cites.
RECIPE: A grammar-based framework for automatically evolving classification pipelines
Alex De Sa, Walter Pinto, Luiz Otavio Oliveira, and Gisele Pappa · 2017
Later among the works it cites.
Meta-learning and universality
Chelsea Finn and Sergey Levine · 2017
Later among the works it cites.
Model-agnostic meta-learning for fast adaptation of deep networks
Chelsea Finn, Pieter Abbeel, and Sergey Levine · 2017
Later among the works it cites.
Probabilistic matrix factorization for automated machine learning
Nicolo Fusi, Rishit Sheth, and Huseyn Melih Elibol · 2017
Later among the works it cites.
Google vizier: A service for black-box optimization
D. Golovin, B. Solnik, S. Moitra, G. Kochanski, J. Karro, and D. Sculley · 2017
Later among the works it cites.
Learning to warm-start Bayesian hyperparameter optimization
J. Kim, S. Kim, and S. Choi · 2017
Later among the works it cites.
Building machines that learn and think like people
Brenden M Lake, Tomer D Ullman, Joshua B Tenenbaum, and Samuel J Gershman · 2017
Later among the works it cites.
Learning to optimize neural nets
Ke Li and Jitendra Malik · 2017
Later among the works it cites.
Alors: An algorithm recommender system
Mustafa Mısır and Michèle Sebag · 2017
Later among the works it cites.
Multiple adaptive Bayesian linear regression for scalable Bayesian optimization with warm start
Valerio Perrone, Rodolphe Jenatton, Matthias Seeger, and Cedric Archambeau · 2017
Later among the works it cites.
autoBagging: Learning to rank bagging workflows with metalearning
Fábio Pinto, Vítor Cerqueira, Carlos Soares, and João Mendes-Moreira · 2017
Later among the works it cites.
Optimization as a model for few-shot learning
Sachin Ravi and Hugo Larochelle · 2017
Later among the works it cites.
Few-shot autoregressive density estimation: Towards learning to learn distributions
Scott Reed, Yutian Chen, Thomas Paine, Aäron van den Oord, SM Eslami, Danilo Rezende, Oriol Vinyals, and Nando de Freitas · 2017
Later among the works it cites.
Informing the use of hyperparameter optimization through metalearning
S. Sanders and C. Giraud-Carrier · 2017
Later among the works it cites.
Prototypical networks for few-shot learning
Jake Snell, Kevin Swersky, and Richard Zemel · 2017
Later among the works it cites.
A meta-learning perspective on cold-start recommendations for items
Manasi Vartak, Arvind Thiagarajan, Conrado Miranda, Jeshua Bratman, and Hugo Larochelle · 2017
Later among the works it cites.
Speeding up Algorithm Selection using Average Ranking and Active Testing by Introducing Runtime
S. Abdulrahman, P. Brazdil, J. van Rijn, and J. Vanschoren · 2018
Closest in time.
Warm-starting deep learning model construction using meta-learning
I. Nur Afif · 2018
Closest in time.
Intelligent assistance for data pre-processing
Besim Bilalli, Alberto Abelló, Tomàs Aluja-Banet, and Robert Wrembel · 2018
Closest in time.
Annotative experts for hyperparameter selection
C. Davis and C. Giraud-Carrier · 2018
Closest in time.
AlphaD3M: Machine learning pipeline synthesis
Iddo Drori, Yamuna Krishnamurthy, Remi Rampin, Raoni de Paula Lourenco, Jorge Piazentin Ono, Kyunghyun Cho, Claudio Silva, and Juliana Freire · 2018
Closest in time.
Efficient Benchmarking of Algorithm Configuration Procedures via Model-Based Surrogates
K. Eggensperger, M. Lindauer, H.H. Hoos, F. Hutter, and K. Leyton-Brown · 2018
Closest in time.
Neural architecture search: A survey
Thomas Elsken, Jan Hendrik Metzen, and Frank Hutter · 2018
Closest in time.
Scalable meta-learning for bayesian optimization using ranking-weighted gaussian process ensembles
Matthias Feurer, Benjamin Letham, and Eytan Bakshy · 2018
Closest in time.
P4ML: A phased performance-based pipeline planner for automated machine learning
Yolanda Gil, Ke-Thia Yao, Varun Ratnakar, Daniel Garijo, Greg Ver Steeg, Pedro Szekely, Rob Brekelmans, Mayank Kejriwal, Fanghao Luo, and I-Hui Huang · 2018
Closest in time.
Recasting gradient-based meta-learning as hierarchical bayes
Erin Grant, Chelsea Finn, Sergey Levine, Trevor Darrell, and Thomas Griffiths · 2018
Closest in time.
Data complexity meta-features for regression problems
Ana Carolina Lorena, Aron I. Maciel, Péricles B. C. de Miranda, Ivan G. Costa, and Ricardo B. C. Prudêncio · 2018
Closest in time.
Use of meta-learning for hyperparameter tuning of classification problems
R.G. Mantovani · 2018
Closest in time.
A simple neural attentive meta-learner
Nikhil Mishra, Mostafa Rohaninejad, Xi Chen, and Pieter Abbeel · 2018
Closest in time.
On first-order meta-learning algorithms
A. Nichol, J. Achiam, and J. Schulman · 2018
Closest in time.
Predicting hyperparameters from meta-features in binary classification problems
E. Nisioti, K. Chatzidimitriou, and A Symeonidis · 2018
Closest in time.
Meta-QSAR: learning how to learn QSARs
I. Olier, N. Sadawi, G.R. Bickerton, J. Vanschoren, C. Grosan, L. Soldatova, and R.D. King · 2018
Closest in time.
Meta-learning transferable active learning policies by deep reinforcement learning
K Pang, M. Dong, Y. Wu, and T. Hospedales · 2018
Closest in time.
Tunability: Importance of hyperparameters of machine learning algorithms
P. Probst, B. Bischl, and A.-L. Boulesteix · 2018
Closest in time.
Meta-learning for semi-supervised few-shot classification
Mengye Ren, Eleni Triantafillou, Sachin Ravi, Jake Snell, Kevin Swersky, Joshua B Tenenbaum, Hugo Larochelle, and Richard S Zemel · 2018
Closest in time.
Towards reproducible empirical research in meta-learning
A. Rivolli, L.P.F. Garcia, C. Soares, J. Vanschoren, and A.C.P.L.F. de Carvalho · 2018
Closest in time.
Feature selection for high-dimensional data: A fast correlation-based filter solution
B. Schoenfeld, C. Giraud-Carrier, M. Poggeman, J. Christensen, and K. Seppi · 2018
Closest in time.
Don’t Rule Out Simple Models Prematurely
Benjamin Strang, Peter van der Putten, Jan N. van Rijn, and Frank Hutter · 2018
Closest in time.
The Online Performance Estimation Framework. Heterogeneous Ensemble Learning for Data Streams
J. van Rijn, G. Holmes, B. Pfahringer, and J. Vanschoren · 2018
Closest in time.
Hyperparameter importance across datasets
J. N. van Rijn and Frank Hutter · 2018
Closest in time.
Importance of tuning hyperparameters of machine learning algorithms
H. Weerts, M. Meuller, and J. Vanschoren · 2018
Closest in time.
Ml-plan for unlimited-length machine learning pipelines
Marcel Wever, Felix Mohr, and Eyke Hüllermeier · 2018
Closest in time.
Scalable Gaussian process-based transfer surrogates for hyperparameter optimization
Martin Wistuba, Nicolas Schilling, and Lars Schmidt-Thieme · 2018
Closest in time.
Oboe: Collaborative filtering for automl initialization
C. Yang, Y. Akimoto, D.W Kim, and M. Udell · 2018
Closest in time.