A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2021; you can also visit the original URL.
The file type is application/pdf.
Filters
In Defense of Uniform Convergence: Generalization via derandomization with an application to interpolating predictors
[article]
2021
arXiv
pre-print
Preserved Fulltext
Other Versions
We propose to study the generalization error of a learned predictor ĥ in terms of that of a surrogate (potentially randomized) predictor that is coupled to ĥ and designed to trade empirical risk for control ...
We also show that replacing ĥ by its conditional distribution with respect to an arbitrary σ-field is a convenient way to derandomize. ...
error of learned classifier via uniform convergence of a suitable derandomized classifier. ...
arXiv:1912.04265v3
fatcat:zse5m4rqanftfpbed2xq45o7aq
On Uniform Convergence and Low-Norm Interpolation Learning
[article]
2021
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 2021; you can also visit the original URL.
The file type is application/pdf.
Other Versions
But we argue we can explain the consistency of the minimal-norm interpolator with a slightly weaker, yet standard, notion: uniform convergence of zero-error predictors in a norm ball. ...
We consider an underdetermined noisy linear regression model where the minimum-norm interpolating predictor is known to be consistent, and ask: can uniform convergence in a norm ball, or at least (following ...
“In Defense of Uniform Con-
vergence: Generalization via derandomization with an application to interpolating predictors.” ...
arXiv:2006.05942v3
fatcat:q6sday3xfzfb5fcertowseduii
Exact Gap between Generalization Error and Uniform Convergence in Random Feature Models
[article]
2021
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 2021; you can also visit the original URL.
The file type is application/pdf.
We show that, in the setting where the classical uniform convergence bound is vacuous (diverges to ∞), uniform convergence over the interpolators still gives a non-trivial bound of the test error of interpolating ...
Recent work showed that there could be a large gap between the classical uniform convergence bound and the actual test error of zero-training-error predictors (interpolators) such as deep neural networks ...
In defense of uni-
form convergence: Generalization via derandomization
with an application to interpolating predictors. In Interna-
tional Conference on Machine Learning, pp. 7263-7272. ...
arXiv:2103.04554v1
fatcat:n2jfpgykpffjbhxkm37sz4dvsm
Explaining generalization in deep learning: progress and fundamental limits
[article]
2021
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 2021; you can also visit the original URL.
The file type is application/pdf.
With this realization in mind, in the last part of the thesis, we will change course and introduce an empirical technique to estimate generalization using unlabeled data. ...
Given its popularity, in this thesis, we will also take a step back to identify the fundamental limits of uniform convergence as a tool to explain generalization. ...
bounds via uniform convergence. ...
arXiv:2110.08922v1
fatcat:blzj6rhlffgrjpeaj2ia57g6gq
The Sample Complexity of One-Hidden-Layer Neural Networks
[article]
2022
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 2022; you can also visit the original URL.
The file type is application/pdf.
We begin by proving that in general, controlling the spectral norm of the hidden layer weight matrix is insufficient to get uniform convergence guarantees (independent of the network width), while a stronger ...
smooth (with the result extending to deeper networks); and second, for certain types of convolutional networks. ...
Acknowledgements This research is supported in part by European Research Council (ERC) grant 754705, and NSF-BSF award 1718970. ...
arXiv:2202.06233v1
fatcat:onrhz4ktvnexpjrrjetfv6hx5a
Data splitting improves statistical performance in overparametrized regimes
[article]
2021
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 2021; you can also visit the original URL.
The file type is application/pdf.
We further provide a unified framework that allows to analyze both the finite and infinite dimensional setting. We numerically demonstrate the effect of different model parameters. ...
While large training datasets generally offer improvement in model performance, the training process becomes computationally expensive and time consuming. ...
In defense of uniform
convergence: Generalization via derandomization with an application to interpolat-
ing predictors. In International Conference on Machine Learning, pages 7263-7272. ...
arXiv:2110.10956v1
fatcat:kggbrkt7onc3pagrmlwfcfp5oy
Dissecting Non-Vacuous Generalization Bounds based on the Mean-Field Approximation
[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
We investigate common explanations, such as the failure of VI due to problems in optimization or choosing a suboptimal prior. ...
Explaining how overparametrized neural networks simultaneously achieve low risk and zero empirical risk on benchmark datasets is an open problem. ...
In defense of
uniform convergence: Generalization via derandomiza-
tion with an application to interpolating predictors. arXiv
preprint arXiv:1912.04265, 2019. ...
arXiv:1909.03009v2
fatcat:beopwgmrabbtnnh4rcvkleye4m
Computer Science in High Performance Sport-Applications and Implications for Professional Coaching (Dagstuhl Seminar 13272)
2013
unpublished
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 acknowledge support from the Strategic Basic Research (SBO) Programme of the Flemish Agency for Innovation through Science and Technology (IWT) in the context of the SPION project 6 under grant agreement ...
These parameters are sent to a smart phone application via ANT+ TM . The measured data is then transmitted to an application server using wireless communication technologies (UMTS, HSUPA). ...
In addition,there appears to be a regime for the number of data points (n) and the number of cluster centers (k) where generated problems where k-means takes much longer to converge. ...
fatcat:yg5vvzymuvcibirco4nawxes4m
Dagstuhl Reports, Volume 6, Issue 11, November 2016, Complete Issue
[article]
2017
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 2022; you can also visit the original URL.
The file type is application/pdf.
, their use in potential functions methods, in SVM, the general "kernel trick", the observation that kernels can be defined on arbitrary sets of objects, the link to GPs, and finally the idea to represent ...
Kernel mean representations lend themselves well to the development of kernel methods for probabilistic programming, i.e., methods for lifting functional operations defined for data types to the same functional ...
time O(n 2 ) and space O( √ n), derandomizing an algorithm of Wang. ...
doi:10.4230/dagrep.6.11
fatcat:tfkdfittpjdydfv7ejvk4bvnh4
2016 Jahresbericht Annual Report
unpublished
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 organizers are all thankful to the participants, who all brought a unique insight to the seminar, which in my humble opinion, succeeded in its aims. ...
The organizers would like to express their gratitude to all participants of the Seminar. ...
Therefore, these boosting techniques lack efficiency in case dependent tasks of an application mapped to two different cores or, in general, for multiple concurrently executing applications with distinctive ...
fatcat:oef4sw3ebbcwhe7qbtizni4lfy