Fetching the paper…
Reading the bibliography…
Information-theoretic approaches to active learning have traditionally focused on maximising the information gathered about the model parameters, most commonly by optimising the BALD score.
Statistical Methods for Research Workers
Fisher (1925) · 1925
Earlier work this paper cites.
On a measure of the information provided by an experiment
Lindley (1956) · 1956
Earlier work this paper cites.
Parameter Estimation in Engineering and Science
Beck & Arnold (1977) · 1977
Earlier work this paper cites.
Estimation of Dependences Based on Empirical Data
Vapnik (1982) · 1982
Earlier work this paper cites.
Queries and concept learning
Angluin (1988) · 1988
Earlier work this paper cites.
Training connectionist networks with queries and selective sampling
Atlas, Cohn, & Ladner (1989) · 1989
Earlier work this paper cites.
Neural network exploration using optimal experiment design
Cohn (1993) · 1993
Earlier work this paper cites.
A sequential algorithm for training text classifiers
Lewis & Gale (1994) · 1994
Earlier work this paper cites.
Bayesian experimental design: a review
Chaloner & Verdinelli (1995) · 1995
Earlier work this paper cites.
Active learning with statistical models
Cohn, Ghahramani, & Jordan (1996) · 1996
Earlier work this paper cites.
On asymptotic properties of predictive distributions
Komaki (1996) · 1996
Earlier work this paper cites.
Gradient-based learning applied to document recognition
LeCun, Bottou, Bengio, & Haffner (1998) · 1998
Earlier work this paper cites.
Ensemble methods in machine learning
Dietterich (2000) · 2000
Earlier work this paper cites.
Gaussian process regression: active data selection and test point rejection
Seo, Wallat, Graepel, & Obermayer (2000) · 2000
Earlier work this paper cites.
Random forests
Breiman (2001) · 2001
Earlier work this paper cites.
Toward optimal active learning through sampling estimation of error reduction
Roy & McCallum (2001) · 2001
Earlier work this paper cites.
The IM algorithm: a variational approach to information maximization
Barber & Agakov (2003) · 2003
Earlier work this paper cites.
Latent Dirichlet allocation
Blei, Ng, & Jordan (2003) · 2003
Earlier work this paper cites.
Combining active learning and semi-supervised learning using Gaussian fields and harmonic functions
Zhu, Lafferty, & Ghahramani (2003) · 2003
Earlier work this paper cites.
Active learning for Parzen window classifier
Chapelle (2005) · 2005
Earlier work this paper cites.
Elements of Information Theory
Cover & Thomas (2005) · 2005
Earlier work this paper cites.
Sparse Gaussian processes using pseudo-inputs
Snelson & Ghahramani (2005) · 2005
Earlier work this paper cites.
Active learning via transductive experimental design
Yu, Bi, & Tresp (2006) · 2006
Earlier work this paper cites.
k-means++: the advantages of careful seeding
Arthur & Vassilvitskii (2007) · 2007
Earlier work this paper cites.
Optimizing estimated loss reduction for active sampling in rank learning
Donmez & Carbonell (2008) · 2008
Earlier work this paper cites.
Near-optimal sensor placements in Gaussian processes: theory, efficient algorithms and empirical studies
Krause, Singh, & Guestrin (2008) · 2008
Earlier work this paper cites.
An analysis of active learning strategies for sequence labeling tasks
Settles & Craven (2008) · 2008
Earlier work this paper cites.
The Elements of Statistical Learning
Hastie, Tibshirani, Friedman, & Friedman (2009) · 2009
Cited alongside, same era.
An informational approach to the global optimization of expensive-to-evaluate functions
Villemonteix, Vazquez, & Walter (2009) · 2009
Cited alongside, same era.
Bayesian Nonparametrics
Hjort, Holmes, Müller, & Walker (2010) · 2010
Cited alongside, same era.
Bayesian active learning for classification and preference learning
Houlsby, Huszár, Ghahramani, & Lengyel (2011) · 2011
Cited alongside, same era.
Scikit-learn: machine learning in Python
Pedregosa, Varoquaux, Gramfort, Michel, Thirion, Grisel, Blondel, Prettenhofer, Weiss, Dubourg, VanderPlas, Passos, Cournapeau, Brucher, Perrot, & Duchesnay (2011) · 2011
Cited alongside, same era.
Entropy search for information-efficient global optimization
Hennig & Schuler (2012) · 2012
Cited alongside, same era.
Differentiable compositional kernel learning for Gaussian processes
Sun, Zhang, Wang, Zeng, Li, & Grosse (2018) · 2018
Later among the works it cites.
Improving genomics-based predictions for precision medicine through active elicitation of expert knowledge
Sundin, Peltola, Micallef, Afrabandpey, Soare, Majumder, Daee, He, Serim, Havulinna, Heckman, Jacucci, Marttinen, & Kaski (2018) · 2018
Later among the works it cites.
Noisy natural gradient as variational inference
Zhang, Sun, Duvenaud, & Grosse (2018) · 2018
Later among the works it cites.
Human-in-the-loop active covariance learning for improving prediction in small data sets
Afrabandpey, Peltola, & Kaski (2019) · 2019
Later among the works it cites.
Reconciling modern machine-learning practice and the classical bias-variance trade-off
Belkin, Hsu, Ma, & Mandal (2019) · 2019
Later among the works it cites.
Variational Bayesian optimal experimental design
alphaXiv searches the wider corpus for related work and actual follow-ups.
alphaXiv is searching for related work…
Matrix Analysis
Horn & Johnson (2012) · 2012
Cited alongside, same era.
Active Learning
Settles (2012) · 2012
Cited alongside, same era.
Scoring rules, divergences and information in Bayesian machine learning
Huszár (2013) · 2013
Cited alongside, same era.
Predictive entropy search for efficient global optimization of black-box functions
Hernández-Lobato, Hoffman, & Ghahramani (2014) · 2014
Cited alongside, same era.
Efficient Bayesian active learning and matrix modelling
Houlsby (2014) · 2014
Cited alongside, same era.
Estimating optimal active learning via model retraining improvement
Evans, Adams, & Anagnostopoulos (2015) · 2015
Cited alongside, same era.
Foster, Jankowiak, Bingham, Horsfall, Teh, Rainforth, & Goodman (2019) · 2019
Later among the works it cites.
BatchBALD: efficient and diverse batch acquisition for deep Bayesian active learning
Kirsch, van Amersfoort, & Gal (2019) · 2019
Later among the works it cites.
BALD-VAE: generative active learning based on the uncertainties of both labeled and unlabeled data
Lee & Kim (2019) · 2019
Later among the works it cites.
Bayesian batch active learning as sparse subset approximation
Pinsler, Gordon, Nalisnick, & Hernández-Lobato (2019) · 2019
Later among the works it cites.
Active learning for decision-making from imbalanced observational data
Sundin, Schulam, Siivola, Vehtari, Saria, & Kaski (2019) · 2019
Later among the works it cites.
Bayesian generative active deep learning
Tran, Do, Reid, & Carneiro (2019) · 2019
Later among the works it cites.
Common Voice: a massively-multilingual speech corpus
Ardila, Branson, Davis, Kohler, Meyer, Henretty, Morais, Saunders, Tyers, & Weber (2020) · 2020
Later among the works it cites.
Deep batch active learning by diverse, uncertain gradient lower bounds
Ash, Zhang, Krishnamurthy, Langford, & Agarwal (2020) · 2020
Later among the works it cites.
Bayesian active learning for production, a systematic study and a reusable library
Atighehchian, Branchaud-Charron, & Lacoste (2020) · 2020
Later among the works it cites.
ThompsonBALD: a new approach to Bayesian batch active learning for deep learning via Thompson sampling
Jeon (2020) · 2020
Later among the works it cites.
Exploring the limits of transfer learning with a unified text-to-text transformer
Raffel, Shazeer, Roberts, Lee, Narang, Matena, Zhou, Li, & Liu (2020) · 2020
Later among the works it cites.
Targeted active learning for Bayesian decision-making
Filstroff, Sundin, Mikkola, Tiulpin, Kylmäoja, & Kaski (2021) · 2021
Later among the works it cites.
Mind your outliers! Investigating the negative impact of outliers on active learning for visual question answering
Karamcheti, Krishna, Fei-Fei, & Manning (2021) · 2021
Later among the works it cites.
Learning transferable visual models from natural language supervision
Radford, Kim, Hallacy, Ramesh, Goh, Agarwal, Sastry, Askell, Mishkin, Clark, Krueger, & Sutskever (2021) · 2021
Later among the works it cites.
Diversity enhanced active learning with strictly proper scoring rules
Tan, Du, & Buntine (2021) · 2021
Later among the works it cites.
Beyond marginal uncertainty: how accurately can Bayesian regression models estimate posterior predictive correlations?
Wang, Sun, & Grosse (2021) · 2021
Later among the works it cites.
Stochastic batch acquisition for deep active learning
Kirsch, Farquhar, Atighehchian, Jesson, Branchaud-Charron, & Gal (2022) · 2022
Later among the works it cites.
A survey on active deep learning: from model driven to data driven
Liu, Wang, Ranjan, He, & Zhao (2022) · 2022
Later among the works it cites.
Towards robust and reproducible active learning using neural networks
Munjal, Hayat, Hayat, Sourati, & Khan (2022) · 2022
Later among the works it cites.
Modern Bayesian experimental design
Rainforth, Foster, Ivanova, & Bickford Smith (2023) · 2023
Closest in time.
Do Bayesian neural networks need to be fully stochastic?
Sharma, Farquhar, Nalisnick, & Rainforth (2023) · 2023
Closest in time.