1 code implementation • 26 Apr 2024 • Rustem Takhanov
To achieve a certain approximation error the required number of neurons in each layer is defined by the RKHS norm of the target function.
no code implementations • 19 Oct 2023 • Rustem Takhanov, Maxat Tezekbayev, Artur Pak, Arman Bolatov, Zhenisbek Assylbekov
In the novel framework, the hardness of a class is usually quantified by the variance of the gradient with respect to a random choice of a target function.
1 code implementation • 2 Oct 2023 • Rustem Takhanov, Maxat Tezekbayev, Artur Pak, Arman Bolatov, Zhibek Kadyrsizova, Zhenisbek Assylbekov
The discrete logarithm problem is a fundamental challenge in number theory with significant implications for cryptographic protocols.
1 code implementation • 25 Jun 2023 • Rustem Takhanov, Y. Sultan Abylkairov, Maxat Tezekbayev
This constraint is included in the objective function as a new term, namely a squared Ky-Fan $k$-antinorm of the Jacobian function.
no code implementations • 27 May 2023 • Rustem Takhanov
For a general language $\Gamma$ and non-positive weights, the minimization task can be carried out in ${\mathcal O}(|V|\cdot |\overline{\Gamma^{\cap}}|^2)$ time.
no code implementations • 1 May 2022 • Rustem Takhanov
The classical Mercer's theorem claims that a continuous positive definite kernel $K({\mathbf x}, {\mathbf y})$ on a compact set can be represented as $\sum_{i=1}^\infty \lambda_i\phi_i({\mathbf x})\phi_i({\mathbf y})$ where $\{(\lambda_i,\phi_i)\}$ are eigenvalue-eigenvector pairs of the corresponding integral operator.
no code implementations • 9 Apr 2022 • Rustem Takhanov
Further, we develop a series of lower bounds on the $\varepsilon$-entropy that can be established from a connection between covering numbers of a ball in RKHS and a quantization of a Gaussian Random Field that corresponds to the kernel $K$ by the Kosambi-Karhunen-Lo\`eve transform.
no code implementations • 27 Jun 2021 • Rustem Takhanov
If ordered singular values of the integral operator associated with $p({\mathbf x}, {\mathbf y})$ die down rapidly, the MMD distance defined by the new symbol $p_r$ differs from the initial one only slightly.
1 code implementation • 23 Dec 2019 • Maxat Tezekbayev, Zhenisbek Assylbekov, Rustem Takhanov
We show that the skip-gram embedding of any word can be decomposed into two subvectors which roughly correspond to semantic and syntactic roles of the word.
1 code implementation • 12 Mar 2019 • Rustem Takhanov
We reformulate unsupervised dimension reduction problem (UDR) in the language of tempered distributions, i. e. as a problem of approximating an empirical probability density function by another tempered distribution, supported in a $k$-dimensional subspace.
no code implementations • 26 Feb 2019 • Zhenisbek Assylbekov, Rustem Takhanov
This paper takes a step towards theoretical analysis of the relationship between word embeddings and context embeddings in models such as word2vec.
no code implementations • 8 Feb 2019 • Abylay Zhumekenov, Malika Uteuliyeva, Olzhas Kabdolov, Rustem Takhanov, Zhenisbek Assylbekov, Alejandro J. Castro
We review neural network architectures which were motivated by Fourier series and integrals and which are referred to as Fourier neural networks.
no code implementations • 19 Aug 2018 • Rustem Takhanov
It turns out that the latter problem allows a reformulation in the dual space, i. e. instead of searching for ${\mathbf g}(P{\mathbf x})$ we suggest searching for its Fourier transform.
1 code implementation • COLING 2018 • Olzhas Kabdolov, Zhenisbek Assylbekov, Rustem Takhanov
We reproduce the Structurally Constrained Recurrent Network (SCRN) model, and then regularize it using the existing widespread techniques, such as naive dropout, variational dropout, and weight tying.
1 code implementation • NAACL 2018 • Zhenisbek Assylbekov, Rustem Takhanov
We propose several ways of reusing subword embeddings and other weights in subword-aware neural language models.
1 code implementation • 2 Sep 2017 • Rustem Takhanov, Zhenisbek Assylbekov
Further, for every word we construct a new sequence over an alphabet of patterns.
1 code implementation • EMNLP 2017 • Zhenisbek Assylbekov, Rustem Takhanov, Bagdat Myrzakhmetov, Jonathan N. Washington
Syllabification does not seem to improve word-level RNN language modeling quality when compared to character-based segmentation.
no code implementations • 22 Apr 2014 • Rustem Takhanov, Vladimir Kolmogorov
We propose a {\em Grammatical Pattern-Based CRF model }(\GPB) that combines the two in a natural way.
no code implementations • 14 Apr 2014 • Vladimir Kolmogorov, Christoph Lampert, Emilie Morvant, Rustem Takhanov
The 38th Annual Workshop of the Austrian Association for Pattern Recognition (\"OAGM) will be held at IST Austria, on May 22-23, 2014.
no code implementations • 1 Oct 2012 • Rustem Takhanov, Vladimir Kolmogorov
(Komodakis & Paragios, 2009) gave an $O(n L)$ algorithm for computing the MAP.