Coresets for Nonparametric Estimation - the Case of DP-Means

By Olivier Bachem, Mario Lucic, Andreas Krause. 2015

114 citations recorded by the source corpus.

Subfields: Probabilistic & Bayesian Methods, Statistical Learning Theory

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Probabilistic & Bayesian Methods

In Statistical Learning Theory

Citations in the corpus

Variational Continual Learning (2017, methodology): “In addition, we extend VCL to include a small episodic memory by combining VI with the coreset data summarization method (Bachem et al., 2015; Huggins et al., 2016).”
Recent Advances of Continual Learning in Computer Vision: An Overview (2021, positive): “[25] proposed Variational Continual Learning (VCL) which combines variational inference and coreset data summarization [173] together.”
Posterior Meta-Replay for Continual Learning (2021, methodology): “An interesting contribution of this method is the mathematically sound posterior update based on coresets (i.e., a small set of samples stored from each task, [62, 3]) within their Bayesian framework.”
BooVAE: Boosting Approach for Continual Learning of VAE (2019, background): “This procedure can also be seen as coreset selection (Huggins et al., 2016; Bachem et al., 2015).”
Functional Regularisation for Continual Learning using Gaussian Processes (2019, methodology): “This technique is straight-forwardly combined with the idea of rehearsals using the coreset data summarisation method (Bachem et al., 2015).”
A Wholistic View of Continual Learning with Deep Neural Networks: Forgotten Lessons and the Bridge to Active and Open World Learning (2020, methodology): “This is not surprising and Bachem et al. (2015) have already argued that k-means with well separated clusters with suﬃciently diﬀerent amount of data points per cluster can be prone to inaccurately estimating multiple cluster centers in highly populated areas versus none in more sparsely populated…”
Automated Scalable Bayesian Inference via Hilbert Coresets (2017, background): “1The concept of a coreset originated in computational geometry and optimization (Agarwal et al., 2005; Feldman and Langberg, 2011; Feldman et al., 2013; Bachem et al., 2015; Lucic et al., 2016; Bachem et al., 2016; Feldman et al., 2011; Han et al., 2016).”
DataComp: In search of the next generation of multimodal datasets (2023, background): “A related line of work develops coreset selection algorithms [55, 3, 42, 7, 87, 136, 28], which aim to select data subsets that lead to the same performance as training on the entire dataset.”
Practical Coreset Constructions for Machine Learning (2017, methodology): “Bachem et al. [2015] ﬁrst show the existence of ε -coresets for the DP-Means clustering problem that are sublinear in the number of data points n if the optimal number of centers k ∗ is sublinear in n .”
Unified Probabilistic Deep Continual Learning through Generative Replay and Open Set Recognition (2019, methodology): “For methods such as iCarl [22] it is therefore common to resort to auxiliary techniques such as a nearest-mean classifier [23] or coresets [24].”
Variational Federated Multi-Task Learning (2019, background): “Finally, it is possible to study VIRTUAL under memory constraints, for which on optimal strategy can store chunks of data for further reﬁnements or discard them, in the line of coresets theory [4].”
Training Mixture Models at Scale via Coresets (2017, methodology): “3 Bounding the Coreset Size Given the pseudo-dimension dimF and some upper bound on the total sensitivity S we may bound the coreset size by using the theorem from Bachem et al. (2017b). A bound on the coreset size can also be obtained by applying the theorem of Feldman and Langberg (2011), where on”
Core‐sets: An updated survey (2019, background): “This allows us to handle regularization terms or costs that are common in machine learning such as to compute X that minimizes cost f ( P , X ) + j X j over every set X of | X | ≤ k centers (P. K. Agarwal & Mustafa, 2004; Bachem, Lucic, & Krause, 2015).”
Training Gaussian Mixture Models at Scale via Coresets (2017, methodology): “…(Feldman et al., 2013b), distributed k -means and k - median (Balcan et al., 2013), dictionary learning (Feldman et al., 2013a), k -segmentation of streaming data (Rosman et al., 2014), non-parametric estimation (Bachem et al., 2015), and clustering with Bregman divergences (Lucic et al., 2016b).”
Distributed Weight Consolidation: A Brain Segmentation Case Study (2018, unknown): “VCL [21] performance was found to be improved by using coresets [1, 12], a small sample of data from the different training sets.”