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`

.

## Filters

##
###
On Boosting with Optimal Poly-Bounded Distributions
[chapter]

2001
*
Lecture Notes in Computer Science
*

We construct a framework which allows an algorithm to turn the

doi:10.1007/3-540-44581-1_32
fatcat:hcmhfchnyjc7rhtuu5krgiwfcu
*distributions*produced by some*boosting*algorithms into polynomially smooth*distributions*(w.r.t. the PAC oracle's*distribution*),*with*minimal ... Our scheme allows the execution of AdaBoost in the*on*-line*boosting*mode (i.e., to perform*boosting*"by filtering"). ... equivalence between*poly*-*distribution*-dependent strong PAC learning and*poly*-*distribution*-dependent weak PAC learning. ...##
###
Distribution-Specific Agnostic Boosting
[article]

2009
*
arXiv
*
pre-print

Conversely, our

arXiv:0909.2927v1
fatcat:4ckz5ryasngmzmu4bxsbgietam
*boosting*algorithm gives a simple hard-core set construction*with*an (almost)*optimal*hard-core set size. ... This allows*boosting*a*distribution*-specific weak agnostic learner to a strong agnostic learner*with*respect to the same*distribution*. ... In order to*bound*the number of*boosting*stages we need to lower*bound*γ ·N h . ...##
###
Optimally-Smooth Adaptive Boosting and Application to Agnostic Learning
[chapter]

2002
*
Lecture Notes in Computer Science
*

This allows adaptively solving problems whose solution is based

doi:10.1007/3-540-36169-3_10
fatcat:nu6xunw5jfhfxam3d32k36auka
*on*smooth*boosting*(like noise tolerant*boosting*and DNF membership learning), while preserving the original (non-adaptive) solution's complexity ... We derive a lower*bound*for the final error achievable by*boosting*in the agnostic model and show that our algorithm actually achieves that accuracy (within a constant factor). ...*On*the*one*hand, non-smoothness obliges to use*boosting*by sampling. ...##
###
Efficient Algorithms for Privately Releasing Marginals via Convex Relaxations
[article]

2013
*
arXiv
*
pre-print

Using private

arXiv:1308.1385v1
fatcat:mkyd5sl3hzgylethpru7kad3dy
*boosting*we are also able to give nearly matching worst-case error*bounds*. Our algorithms are based*on*the geometric techniques of Nikolov, Talwar, and Zhang. ... In this work we present a polynomial time algorithm that, for any*distribution**on*marginal queries, achieves average error at most Õ(√(n) d^ k/2 /4). ... The above approach gives us average error*bounds*for any*distribution**on*queries. To get a worst case error*bound*, we use the*Boosting*for Queries framework of [15] . ...##
###
Page 8146 of Mathematical Reviews Vol. , Issue 2004j
[page]

2004
*
Mathematical Reviews
*

Servedio, Smooth

*boosting*and learning*with*mali- cious noise (473—489); Nader H. Bshouty and Dmitry Gavinsky,*On**boosting**with**optimal**poly*-*bounded**distributions*(490-506); Shai Ben-David, Philip M. ... additive models online*with*fast evaluating kernels (444-460); Shie Mannor and Ron Meir, Geometric*bounds*for generalization in*boosting*(461—472). ...##
###
Efficient Algorithms for Privately Releasing Marginals via Convex Relaxations

2015
*
Discrete & Computational Geometry
*

Using private

doi:10.1007/s00454-015-9678-x
fatcat:ztwwmcdminat7nmp2ubmrpixsa
*boosting*we are also able to give nearly matching worst-case error*bounds*. Our algorithms are based*on*the geometric techniques of Nikolov, Talwar, and Zhang. ... In this work we present a polynomial time algorithm that, for any*distribution**on*marginal queries, achieves average error at mostÕ( √ nd ⌈k/2⌉ 4 ). ... The above approach gives us average error*bounds*for any*distribution**on*queries. To get a worst case error*bound*, we use the*Boosting*for Queries framework of [15] . ...##
###
Improved Distributed Approximations for Maximum Independent Set

2020
*
International Symposium on Distributed Computing
*

*One*may wonder whether it is possible to approximate MaxIS

*with*high probability in fewer than

*poly*(log log n) rounds. ... However, it is unclear how to convert this algorithm to

*one*that succeeds

*with*high probability without sacrificing a large number of rounds. ... To lower

*bound*the size of the obtained independent set I,

*one*therefore just needs to get a lower

*bound*

*on*the sum of the increment probabilities Pr[v t ∈ I|I t−1 ]. 35:8 Improved

*Distributed*Approximations ...

##
###
Boosting Variational Inference: an Optimization Perspective
[article]

2018
*
arXiv
*
pre-print

Variational inference is a popular technique to approximate a possibly intractable Bayesian posterior

arXiv:1708.01733v2
fatcat:35kinigowza6pbzuzvgrhwxwxu
*with*a more tractable*one*. ... Recently,*boosting*variational inference has been proposed as a new paradigm to approximate the posterior by a mixture of densities by greedily adding components to the mixture. ... If the set A contains truncated Gaussian*distributions**with*non-degenerate covariance matrix but*with*small enough determinant to perfectly approximate any density defined*on*a*bounded*support it also ...##
###
Learning Halfspaces with Malicious Noise
[chapter]

2009
*
Lecture Notes in Computer Science
*

We give

doi:10.1007/978-3-642-02927-1_51
fatcat:hk66wrjug5ebtjfsxpczwqaqmy
*poly*(n, 1/ε)-time algorithms for solving the following problems to accuracy ε: • Learning origin-centered halfspaces in R n*with*respect to the uniform*distribution**on*the unit ball*with*malicious ... (The best previous result was Ω(ε/(n log(n/ε)) 1/4 ).) • Learning origin-centered halfspaces*with*respect to any isotropic logconcave*distribution**on*R n*with*malicious noise rate η = Ω(ε 3 / log 2 (n/ ... (The extra factor of ε in the*bound*of Theorem 2 compared*with*Theorem 1 comes from the fact that the*boosting*algorithm constructs "1/ε-skewed"*distributions*.) ...##
###
Martingale Boosting
[chapter]

2005
*
Lecture Notes in Computer Science
*

Martingale

doi:10.1007/11503415_6
fatcat:aakbf45cxzfz5ign74eyjkan5y
*boosting*is a simple and easily understood technique*with*a simple and easily understood analysis. ... A slight variant of the approach provably achieves*optimal*accuracy in the presence of misclassification noise. ... Conclusion We are working*on*implementing the algorithm and evaluating its performance and noise tolerance*on*real world data. ...##
###
Optimal Bounds on Approximation of Submodular and XOS Functions by Juntas

2016
*
SIAM journal on computing (Print)
*

It relies crucially

doi:10.1137/140958207
fatcat:id7g5y2pfbcwjij6u2yhtishp4
*on*our approximation by junta result. As follows from the lower*bounds*in [1] both of these algorithms are close to*optimal*. ... Our uniform*distribution*algorithm runs in time 2 1/*poly*(γ )*poly*(n). ...*One*of the key pieces of the proof is the use a "*boosting*lemma 1 "*on*down-monotone events of Goemans and Vondrak [26] . ...##
###
Optimal Bounds on Approximation of Submodular and XOS Functions by Juntas

2013
*
2013 IEEE 54th Annual Symposium on Foundations of Computer Science
*

It relies crucially

doi:10.1109/focs.2013.32
dblp:conf/focs/FeldmanV13
fatcat:wpq2nientjb2he6em6psgfwwz4
*on*our approximation by junta result. As follows from the lower*bounds*in [1] both of these algorithms are close to*optimal*. ... Our uniform*distribution*algorithm runs in time 2 1/*poly*(γ )*poly*(n). ...*One*of the key pieces of the proof is the use a "*boosting*lemma 1 "*on*down-monotone events of Goemans and Vondrak [26] . ...##
###
Optimal bounds on approximation of submodular and XOS functions by juntas

2014
*
2014 Information Theory and Applications Workshop (ITA)
*

It relies crucially

doi:10.1109/ita.2014.6804263
dblp:conf/ita/FeldmanV14
fatcat:gxjyiofvrfdyxdgf6dfyrkdsaa
*on*our approximation by junta result. As follows from the lower*bounds*in [1] both of these algorithms are close to*optimal*. ... Our uniform*distribution*algorithm runs in time 2 1/*poly*(γ )*poly*(n). ...*One*of the key pieces of the proof is the use a "*boosting*lemma 1 "*on*down-monotone events of Goemans and Vondrak [26] . ...##
###
Boosting and Differential Privacy

2010
*
2010 IEEE 51st Annual Symposium on Foundations of Computer Science
*

Combining this

doi:10.1109/focs.2010.12
dblp:conf/focs/DworkRV10
fatcat:figgtroohrfjvjplnf46oiygoa
*with*evolution of confidence arguments from the literature, we get stronger*bounds**on*the expected cumulative privacy loss due to multiple mechanisms, each of which provides ε-differential ... Given a base synopsis generator that takes a*distribution**on*Q and produces a "weak" synopsis that yields "good" answers for a majority of the weight in Q, our*Boosting*for Queries algorithm obtains a ... We say that M is a (k, λ, η, β)base synopsis generator if for any*distribution*D*on*Q, when M is activated*on*a database x ∈ X n and*on*k queries sampled independently from D,*with*all but β probability ...##
###
Logarithmic Time One-Against-Some
[article]

2016
*
arXiv
*
pre-print

We show that several simple techniques give rise to an algorithm that can compete

arXiv:1606.04988v2
fatcat:7laxfux7djarfhwuo2orv4xbxe
*with**one*-against-all in both space and predictive power while offering exponential improvements in speed when the number ... Compared to previous approaches, we obtain substantially better statistical performance for two reasons: First, we prove a tighter and more complete*boosting*theorem, and second we translate the results ...*With*this criterion we are in a position to directly*optimize*information*boosting*. Definition 1. ...
« Previous

*Showing results 1 — 15 out of 11,120 results*