A training glossary devoted to the course by Elizaveta Tikhomirova.
assessment
noun, countable
a calculation about the cost or value of something
Example: Joinability assessment is highly intractable with pairwise comparisons of raw data, but KHLL enables joinability approximation based on its compact data structures (sketches).
P. H. Chia et al., "KHyperLogLog: Estimating Reidentifiability and Joinability of Large Data at Scale," 2019 IEEE Symposium on Security and Privacy (SP), 2019, pp. 350-364, doi: 10.1109/SP.2019.00046.
ru: оценка
corroborate
verb, transitive
to provide information that supports or helps to prove someone else’s statement, idea etc
Example: Thus, we tried to understand the relationships by using our prediction model to corroborate if they are supported by the medical literature.
Source: K. Fernandes, D. Chicco, J. Cardoso, and J. Fernández, “Supervised deep learning embeddings for the prediction of cervical cancer diagnosis”, PeerJ Computer Science, vol. 4., e154., May 2018, doi: 10.7717/peerj-cs.154
ru: подкреплять
custodian
noun, countable
someone who is responsible for looking after something important or valuable
Example: The ability to estimate the reidentifiability of data sets automatically and efficiently reduces the work required of data custodians to manually label the different data sets.
P. H. Chia et al., "KHyperLogLog: Estimating Reidentifiability and Joinability of Large Data at Scale," 2019 IEEE Symposium on Security and Privacy (SP), 2019, pp. 350-364, doi: 10.1109/SP.2019.00046.
ru: хранитель, страж
cytology
noun, countable
the scientific study of cells from living things
Example: Thereby, we cover scenarios where only
behavioral and demographic information is observable (first line of each table with empty
subset) up to settings where cytology and colposcopy (Hinselmann and Schiller)
results are available.
Source: K. Fernandes, D. Chicco, J. Cardoso, and J. Fernández, “Supervised deep learning
embeddings for the prediction of cervical cancer diagnosis”, PeerJ Computer Science, vol.
4., e154., May 2018, doi: 10.7717/peerj-cs.154
ru: цитология
factor
noun, countable
a number that divides into another number exactly
Example: Taking into account the lower bound in Lemma 2, they must be within a factor of two of the optimal features defined without reference to training outputs under the assumption of Lemma 2.
D. R. Burt, C. E. Rasmussen, and M. van der Wilk, “Convergence of Sparse Variational Inference in Gaussian Processes Regression,” Journal of Machine Learning Research, vol. 21, no. 131, pp. 1-63, 2020.
ru: множитель, коэффициент
feasible
adjective
a plan, idea, or method that is feasible is possible and is likely to work
Example: While all quantities of interest have analytic expressions, their computation is infeasible for large datasets due to the O(N^3) time omplexity of the determinant and inverse.
D. R. Burt, C. E. Rasmussen, and M. van der Wilk, “Convergence of Sparse Variational Inference in Gaussian Processes Regression,” Journal of Machine Learning Research, vol. 21, no. 131, pp. 1-63, 2020.
ru: достижимый
gauge
verb, transitive
to measure or calculate something by using a particular instrument or method
Example: To gauge the reidentifiability of UAs, one can estimate the uniqueness distribution by counting the number of unique IDs that individual UA strings associate with.
P. H. Chia et al., "KHyperLogLog: Estimating Reidentifiability and Joinability of Large Data at Scale," 2019 IEEE Symposium on Security and Privacy (SP), 2019, pp. 350-364, doi: 10.1109/SP.2019.00046.
ru: измерять, оценивать
imputation
noun, uncountable
a method of calculating the value of something when you do not know what the actual value is
Example: Therefore, we added a flag feature that allows the model to identify if the question was answered or not after missing value imputation.
Source: K. Fernandes, D. Chicco, J. Cardoso, and J. Fernández, “Supervised deep learning embeddings for the prediction of cervical cancer diagnosis”, PeerJ Computer Science, vol. 4., e154., May 2018, doi: 10.7717/peerj-cs.154
ru: вменение
induce
verb, transitive
to cause a particular physical condition
Example: We show that under intuitive assumptions the number of inducing variables only needs to grow at a sublinear rate for the KL between the approximation and the posterior to go to zero.
D. R. Burt, C. E. Rasmussen, and M. van der Wilk, “Convergence of Sparse Variational Inference in Gaussian Processes Regression,” Journal of Machine Learning Research, vol. 21, no. 131, pp. 1-63, 2020.
ru: вызывать, побуждать
inherent
adjective
a quality that is inherent in something is a natural part of it and cannot be separated from it
Example: Whether this is an artifact of the proof, the initialization scheme, or an inherent limitation for inducing points is an interesting area for future work.
D. R. Burt, C. E. Rasmussen, and M. van der Wilk, “Convergence of Sparse Variational Inference in Gaussian Processes Regression,” Journal of Machine Learning Research, vol. 21, no. 131, pp. 1-63, 2020.
ru: присущий, неотъемлемый
instantiate
verb, transitive
to represent or be an example of something
Example: In a nutshell, our contribution can be summarized as follows: (i) ... (iii) we showed that multitask autoencoders based on neural
networks can be used as a specific instance to solve this problem, and we instantiated
this idea to model an individual patient’s risk of having cervical cancer.
Source: K. Fernandes, D. Chicco, J. Cardoso, and J. Fernández, “Supervised deep learning embeddings for the prediction of cervical cancer diagnosis”, PeerJ Computer Science, vol. 4., e154., May 2018, doi: 10.7717/peerj-cs.154
ru: создавать экземпляр
leverage
noun, uncountable
influence that you can use to make people do what you want
Example: Li et al. [2016] use an approximate k-DPP, nearly identical to the initialization we analyze; Alaoui & Mahoney [2015] sample columns according to ridge leverage scores.
D. R. Burt, C. E. Rasmussen, and M. van der Wilk, “Convergence of Sparse Variational Inference in Gaussian Processes Regression,” Journal of Machine Learning Research, vol. 21, no. 131, pp. 1-63, 2020.
ru: способ достижения цели, усилие рычага
mitigate
verb, transitive
to make a situation or the effects of something less unpleasant, harmful, or serious
Example: In other cases, we have mitigated joinability risks by dropping certain fields entirely, or by ensuring that the access control lists of both data sets are disjoint.
P. H. Chia et al., "KHyperLogLog: Estimating Reidentifiability and Joinability of Large Data at Scale," 2019 IEEE Symposium on Security and Privacy (SP), 2019, pp. 350-364, doi: 10.1109/SP.2019.00046.
ru: смягчать
modality
noun, countable
a particular way of doing or experiencing something
Example: The relative gains in terms of area under the PR
curve depend on the subset of observable modalities, ranging from 30.7% when only
medical records are observed to 3.3% when the outcome of all the screening procedures
is known.
Source: K. Fernandes, D. Chicco, J. Cardoso, and J. Fernández, “Supervised deep learning embeddings for the prediction of cervical cancer diagnosis”, PeerJ Computer Science, vol. 4., e154., May 2018, doi: 10.7717/peerj-cs.154
ru: модальность
proprietary
adjective
a proprietary product is one that is sold under a trade name (opposed to generic)
Example: We have validated that KHLL is fast, parallelizable and accurate on both proprietary and public data sets.
P. H. Chia et al., "KHyperLogLog: Estimating Reidentifiability and Joinability of Large Data at Scale," 2019 IEEE Symposium on Security and Privacy (SP), 2019, pp. 350-364, doi: 10.1109/SP.2019.00046.
