A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2012; you can also visit the original URL.
The file type is application/pdf.
Filters
Empirical lower bounds on the complexity of translational equivalence
2006
Proceedings of the 21st International Conference on Computational Linguistics and the 44th annual meeting of the ACL - ACL '06
Preserved Fulltext
This paper describes a study of the patterns of translational equivalence exhibited by a variety of bitexts. ...
The study found that the complexity of these patterns in every bitext was higher than suggested in the literature. ...
The inevitable noise in the data motivated us to focus on lower bounds, complementary to Fox (2002) , who wrote that her results "should be looked on as more of an upper bound." ...
doi:10.3115/1220175.1220298
dblp:conf/acl/WellingtonWM06
fatcat:6en7j4gyozggtl3yaifjavy5ky
Page 6754 of Mathematical Reviews Vol. , Issue 95k
[page]
1995
Mathematical Reviews
Preserved Fulltext
The Internet Archive has digitized a microfilm copy of this work. It may be possible to borrow a copy for reading.
We apply this result to obtain an upper bound on the combinatorial complexity of the ‘lower envelope’ of the space of all rays in 3- space that lie above a given polyhedral terrain K with n edges. ...
Summary: “We consider the problem of bounding the complexity of the lower envelope of surface patches in 3-space, all algebraic of constant maximum degree, and bounded by algebraic arcs of constant maximum ...
Empirical Gaussian priors for cross-lingual transfer learning
[article]
2016
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2019; you can also visit the original URL.
The file type is application/pdf.
Finally, we note that using empirical Gaussian priors leads to much lower Rademacher complexity, and is superior to optimally weighted model interpolation. ...
In cross-lingual part-of-speech (POS) tagging, our target language training data consists of sequences of sentences with word-by-word labels projected from translations in k languages for which we have ...
(ii) Also, consider the obvious extension of using empirical Gaussian priors in the multi-source set-up, where we regularize the target to stay in one of several bounding ellipsoids rather than the one ...
arXiv:1601.02166v1
fatcat:fbjqdi7kp5gyjgfks4e6f3zqy4
Page 4364 of Mathematical Reviews Vol. , Issue 2001F
[page]
2001
Mathematical Reviews
Preserved Fulltext
The Internet Archive has digitized a microfilm copy of this work. It may be possible to borrow a copy for reading.
Summary: “We obtain minimax lower and upper bounds for the expected distortion redundance of empirically designed vec- tor quantizers. ...
Summary (translated from the Russian): “We obtain a lower bound for the error probability of recognizing a quasiperiodic sequence, formed from pulses of identical form and duration with unknown start times ...
Translating Idiomatic Expressions from English into Arabic: Difficulties and Strategies
2017
Social Science Research Network
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
Translation is the process of rendering aspects and features of a target text semantically, culturally and pragmatically into another language. ...
However, translating idiomatic and culturally-bound expressions has been a challenge for translators as they are culture-bound and involve many cultural elements. ...
His teaching and research interests include translation and interpreting, sociolinguistics, and language teaching methodology. ...
doi:10.2139/ssrn.2898623
fatcat:qz6tvszjnzavlbmdu3g46ksvb4
Differentially Private Release and Learning of Threshold Functions
2015
2015 IEEE 56th Annual Symposium on Foundations of Computer Science
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2018; you can also visit the original URL.
The file type is application/pdf.
We prove new upper and lower bounds on the sample complexity of (ε, δ) differentially private algorithms for releasing approximate answers to threshold functions. ...
The lower bound gives the first separation between the sample complexity of properly learning a concept class with (ε, δ) differential privacy and learning without privacy. ...
We also thank Gautam Kamath for pointing us to references on distribution learning. ...
doi:10.1109/focs.2015.45
dblp:conf/focs/BunNSV15
fatcat:mp4ybdbxmvccpmqzpzyj6l43hq
Lower Bounds on Adversarial Robustness from Optimal Transport
[article]
2019
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
Other Versions
When the classifier comes from a restricted hypothesis class, the optimal transportation cost provides a lower bound. ...
We apply our framework to the case of Gaussian data with norm-bounded adversaries and explicitly show matching bounds for the classification and transport problems as well as the optimality of linear classifiers ...
robustness) using optimal transport, ii) we show matching upper and lower bounds for adversarial robustness as well as the sample complexity of attaining it for the case of Gaussian data and a convex, ...
arXiv:1909.12272v2
fatcat:niacuvjbjzhi5jwv5tzkaufiia
Page 1169 of Mathematical Reviews Vol. , Issue 98B
[page]
1998
Mathematical Reviews
Preserved Fulltext
The Internet Archive has digitized a microfilm copy of this work. It may be possible to borrow a copy for reading.
Summary (translated from the Russian): “We present a method for obtaining lower bounds on complexity for schemes of the concatenation of words. ...
(RS-AOSSI; Novosibirsk)
A lower bound on complexity for schemes of the concatenation of words. (Russian. Russian summary)
Diskret. Anal. Issled. Oper. 3 (1996), no. 1, 52-56, 93. ...
Page 4962 of Mathematical Reviews Vol. , Issue 99g
[page]
1999
Mathematical Reviews
Preserved Fulltext
The Internet Archive has digitized a microfilm copy of this work. It may be possible to borrow a copy for reading.
Moreover by giving upper and lower bounds we show that without space restrictions the worst case query complexity of planar point location differs from log, n + 2,/log, n at most by an additive factor ...
“For the case of linear space we show the query complexity to be bounded by log, n + 2,/log, n + O(log'/4 n).” ...
Page 6710 of Mathematical Reviews Vol. , Issue 2000i
[page]
2000
Mathematical Reviews
Preserved Fulltext
The Internet Archive has digitized a microfilm copy of this work. It may be possible to borrow a copy for reading.
“We then give an empirical evaluation of the strength of the various lower bounds and heuristics. ...
“We establish a number of facts about the relationship between these different sorts of lower bounds, including the equivalence of certain linear-programming-based lower bounds for both of these problems ...
The role of invariance in spectral complexity-based generalization bounds
[article]
2020
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
Other Versions
Focusing on the case of spectral complexity we investigate theoretically and empirically the insensitivity of the complexity measure to invariances relevant to CNNs, and show several limitations of spectral ...
For a specific formulation of spectral complexity we show that it results in the same upper bound complexity estimates for convolutional and locally connected architectures (which don't have the same favorable ...
As we increase the number of translations/elastic deformations (equivalently decrease the percentage of the base space) the slopes of the GE curves decrease and we tend to have lower GE for the same spectral ...
arXiv:1905.09677v2
fatcat:qqdtigbwovax3fx5dr3svnqzlq
Precision-Recall versus Accuracy and the Role of Large Data Sets
2019
PROCEEDINGS OF THE THIRTIETH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE AND THE TWENTY-EIGHTH INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE CONFERENCE
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
The basic theorems of statistical learning establish the number of examples needed to estimate the accuracy of a classifier as a function of its complexity (VC-dimension) and the confidence desired; the ...
By contrast, the standard theoretical analysis of machine learning admits no dependence on the imbalance of classes at all. ...
As a corollary, we obtain tight bounds on the sample complexity of precision-recall bounds. ...
doi:10.1609/aaai.v33i01.33014039
fatcat:ciquwetxp5hopavxqvgnntfy3m
THE PROPER USE OF RISK MEASURES IN PORTFOLIO THEORY
2005
International Journal of Theoretical and Applied Finance
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2017; you can also visit the original URL.
The file type is application/pdf.
Finally, we propose an empirical comparison among three different portfolio choice models which depend on the mean, on a risk measure, and on a skewness parameter. ...
Thus, we assess and value the impact on the investor's preferences of three different risk measures even considering some derivative assets among the possible choices. ...
on the arc EA is lower than the expected utility of some portfolios on the arc AB. ...
doi:10.1142/s0219024905003402
fatcat:tll5s4rpvng6bexirdhs7cyatu
Finding and proving the exact ground state of a generalized Ising model by convex optimization and MAX-SAT
2016
Physical review B
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2018; you can also visit the original URL.
The file type is application/pdf.
Other Versions
We transform the infinite-discrete-optimization problem into a pair of combinatorial optimization (MAX-SAT) and non-smooth convex optimization (MAX-MIN) problems, which provide upper and lower bounds on ...
In this article, we present the first general algorithm to find the exact ground states of complex lattice models and to prove their global optimality, resolving this fundamental problem in condensed matter ...
In addition, some of the test cases for ground states were supported by the Office of Naval Research under contract N00014-14-1-0444. ...
doi:10.1103/physrevb.94.134424
fatcat:p4bcsn6ufjex5ovh3ejgqn6j7y
Page 8071 of Mathematical Reviews Vol. , Issue 98M
[page]
1998
Mathematical Reviews
Preserved Fulltext
The Internet Archive has digitized a microfilm copy of this work. It may be possible to borrow a copy for reading.
{For the entire collection see MR 98k:03004.}
98m:68053 68P20
Gasanoy, E. E.
A lower bound for the complexity of information networks for a partial ordering relation. (Russian. ...
Using this property, we obtain a lower bound for search problems with a natural partial ordering relation given on the Boolean cube. ...
« Previous
Showing results 1 — 15 out of 125,572 results