1 |
EFFECTIVE CONCEPT CLASSES OF PAC AND PACi INCOMPARABLE DEGREES, JOINS AND EMBEDDING OF DEGREESSenadheera, Dodamgodage Gihanee Madumalika 01 August 2022 (has links)
The ordering of concept classes under PAC reducibility is nonlinear, even when restricted to particular concrete examples. We construct two effective concept classes of incomparable PAC degrees to show that there exist incomparable PAC degrees, analogous to incomparable Turing degrees. The non-learnability of concept classes in the PAC learning model is explained by the existence of PAC incomparable degrees. It was necessary to deal with the size of an effective concept class thus we propose a method to compute the size of the effective concept class using Kolmogorov complexity. To define the jump operator for PACi degrees the join of effective concept classes is constructed and explores the possibility of embedding known degrees to PACi or PAC degrees. If an embedding exists it will enable proving properties of known degrees for PACi and PAC degrees without explicitly proving them.
|
2 |
PAC-learning with label noiseJabbari Arfaee, Shahin 06 1900 (has links)
One of the main criticisms of previously studied label noise models in the PAC-learning framework is the inability of such models to represent the noise in real world data. In this thesis, we study this problem by introducing a framework for modeling label noise and suggesting four new
label noise models. We prove positive learnability results for these noise models in learning simple concept classes and discuss the difficulty of the problem of learning other interesting concept classes under these new models. In addition, we study the previous general learning algorithm,
called the minimum pn-disagreement strategy, that is used to prove learnability results in the PAC-learning framework both in the absence and presence of noise. Because of limitations of the minimum pn-disagreement strategy, we propose a new general learning algorithm called the minimum
nn-disagreement strategy. Finally, for both minimum pn-disagreement strategy and minimum nn-disagreement strategy, we investigate some properties of label noise models that provide sufficient conditions for the learnability of specific concept classes.
|
3 |
PAC-learning with label noiseJabbari Arfaee, Shahin Unknown Date
No description available.
|
4 |
On Learning k-Parities and the Complexity of k-Vector-SUMGadekar, Ameet January 2016 (has links) (PDF)
In this work, we study two problems: first is one of the central problem in learning theory of learning sparse parities and the other k-Vector-SUM is an extension of the not oriousk-SUM problem. We first consider the problem of learning k-parities in the on-line mistake-bound model: given a hidden vector ∈ {0,1}nwith|x|=kand a sequence of “questions” a ,a ,12··· ∈{0,1}n, where the algorithm must reply to each question with〈a ,xi〉(mod 2), what is the best trade off between the number of mistakes made by the algorithm and its time complexity? We improve the previous best result of Buhrman et. al. By an exp (k) factor in the timecomplexity. Next, we consider the problem of learning k-parities in the presence of classification noise of rate η∈(0,12). A polynomial time algorithm for this problem (whenη >0 andk=ω(1))is a longstanding challenge in learning theory. Grigorescu et al. Showed an algorithm running in time(no/2)1+4η2+o(1). Note that this algorithm inherently requires time(nk/2)even when the noise rateη is polynomially small. We observe that for sufficiently small noise rate, it ispossible to break the(nk/2)barrier. In particular, if for some function f(n) =ω(logn) andα∈[12,1),k=n/f(n) andη=o(f(n)−α/logn), then there is an algorithm for the problem with running time poly(n)·( )nk1−α·e−k/4.01.Moving on to the k-Vector-SUM problem, where given n vectors〈v ,v ,...,v12n〉over the vector space Fdq, a target vector tand an integer k>1, determine whether there exists k vectors whose sum list, where sum is over the field Fq. We show a parameterized reduction fromk-Clique problem to k-Vector-SUM problem, thus showing the hardness of k-Vector-SUM. In parameterized complexity theory, our reduction shows that the k-Vector-SUM problem is hard for the class W[1], although, Downey and Fellows have shown the W[1]-hardness result for k-Vector-SUM using other techniques. In our next attempt, we try to show connections between k-Vector-SUM and k-LPN. First we prove that, a variant of k-Vector-SUM problem, called k-Noisy-SUM is at least as hard as the k-LPN problem. This implies that any improvements ink-Noisy-SUM would result into improved algorithms fork-LPN. In our next result, we show a reverse reduction from k-Vector-SUM to k-LPN with high noise rate. Providing lower bounds fork-LPN problem is an open challenge and many algorithms in cryptography have been developed assuming its1 2hardness. Our reduction shows that k-LPN with noise rate η=12−12·nk·2−n(k−1k)cannot be solved in time no(k)assuming Exponential Time Hypothesis and, thus providing lower bound for a weaker version of k-LPN
|
5 |
Slovinské národní divadlo v Lublani / Slovene National Theatre in LjubljanaHýl, Petr January 2009 (has links)
SLOVENE NATIONAL THEATRE IN LJUBLJANA Author Report Of The Diploma Work Author: Bc. Petr Hýl Supervisor: doc. ing. arch. Zdeněk Makovský
|
Page generated in 0.0315 seconds