[کتاب][B] Analysis of boolean functions

R O'Donnell - 2014‏ - books.google.com
Boolean functions are perhaps the most basic objects of study in theoretical computer
science. They also arise in other areas of mathematics, including combinatorics, statistical …

Discriminative K-SVD for dictionary learning in face recognition

Q Zhang, B Li - 2010 IEEE computer society conference on …, 2010‏ - ieeexplore.ieee.org
In a sparse-representation-based face recognition scheme, the desired dictionary should
have good representational power (ie, being able to span the subspace of all faces) while …

[کتاب][B] Boolean functions: Theory, algorithms, and applications

Y Crama, PL Hammer - 2011‏ - books.google.com
Written by prominent experts in the field, this monograph provides the first comprehensive,
unified presentation of the structural, algorithmic and applied aspects of the theory of …

Agnostic learning of monomials by halfspaces is hard

V Feldman, V Guruswami, P Raghavendra… - SIAM Journal on …, 2012‏ - SIAM
We prove the following strong hardness result for learning: Given a distribution of labeled
examples from the hypercube such that there exists a monomial consistent with (1-ϵ) of the …

Understanding influence functions and datamodels via harmonic analysis

N Saunshi, A Gupta, M Braverman, S Arora - arxiv preprint arxiv …, 2022‏ - arxiv.org
Influence functions estimate effect of individual data points on predictions of the model on
test data and were adapted to deep learning in Koh and Liang [2017]. They have been used …

Bounded independence fools halfspaces

I Diakonikolas, P Gopalan, R Jaiswal… - SIAM Journal on …, 2010‏ - SIAM
We show that any distribution on {-1,+1\}^n that is k-wise independent fools any halfspace
(or linear threshold function) h:{-1,+1\}^n→{-1,+1\}, ie, any function of the form …

Property testing: A learning theory perspective

D Ron - Foundations and Trends® in Machine Learning, 2008‏ - nowpublishers.com
Property testing deals with tasks where the goal is to distinguish between the case that an
object (eg, function or graph) has a prespecified property (eg, the function is linear or the …

Testing Fourier dimensionality and sparsity

P Gopalan, R O'Donnell, RA Servedio, A Shpilka… - SIAM Journal on …, 2011‏ - SIAM
We present a range of new results for testing properties of Boolean functions that are
defined in terms of the Fourier spectrum. Broadly speaking, our results show that the …

New algorithms and lower bounds for monotonicity testing

X Chen, RA Servedio, LY Tan - 2014 IEEE 55th Annual …, 2014‏ - ieeexplore.ieee.org
We consider the problem of testing whether an unknown Boolean function f:{-1, 1} n→{-1, 1}
is monotone versus ε-far from every monotone function. The two main results of this paper …

A polynomial lower bound for testing monotonicity

A Belovs, E Blais - Proceedings of the forty-eighth annual ACM …, 2016‏ - dl.acm.org
We show that every algorithm for testing n-variate Boolean functions for monotonicityhas
query complexity Ω (n 1/4). All previous lower bounds for this problem were designed for …