Filters








10,195 Hits in 7.5 sec

Second-order Symmetric Non-negative Latent Factor Analysis [article]

Weiling Li, Xin Luo
<span title="2022-03-04">2022</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
The undirected network representation task can be efficiently addressed by a symmetry non-negative latent factor (SNLF) model, whose objective is clearly non-convex.  ...  Aiming at addressing this issue, this study proposes to incorporate an efficient second-order method into SNLF, thereby establishing a second-order symmetric non-negative latent factor analysis model for  ...  insight of SNLF model, the symmetric non-negative latent two-fold ideas: a) incorporating a mapping strategy into SNLF model factor models are proposed [12, 13].  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2203.02088v1">arXiv:2203.02088v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/qmrkbtn6zzhctnkpguka5belv4">fatcat:qmrkbtn6zzhctnkpguka5belv4</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20220307022107/https://arxiv.org/ftp/arxiv/papers/2203/2203.02088.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/19/32/1932f8dec0e5ce03642cebc7f7ae9ec8821a9dcd.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2203.02088v1" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>

Accelerated parallel and distributed algorithm using limited internal memory for nonnegative matrix factorization

Duy Khuong Nguyen, Tu Bao Ho
<span title="2016-10-04">2016</span> <i title="Springer Nature"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/dpj4kespnjdflemhwaulft4tm4" style="color: black;">Journal of Global Optimization</a> </i> &nbsp;
Nonnegative matrix factorization (NMF) is a powerful technique for dimension reduction, extracting latent factors and learning part-based representation.  ...  Keywords Non-negative matrix factorization · Accelerated anti-lopsided algorithm · Cooridinate descent algorithm · Parallel and distributed algorithm  ...  Hence, NMF can be considered as a latent factor model of latent components W , and learning this model is equivalent to find out latent components W .  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1007/s10898-016-0471-z">doi:10.1007/s10898-016-0471-z</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/x6nyvaic5fhaxk5r7mf6hxvm6m">fatcat:x6nyvaic5fhaxk5r7mf6hxvm6m</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20190218161154/http://pdfs.semanticscholar.org/0f9f/78b6f3214b0663d252caf3f55eb779feaec3.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/0f/9f/0f9f78b6f3214b0663d252caf3f55eb779feaec3.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1007/s10898-016-0471-z"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> springer.com </button> </a>

Modified Cholesky Riemann Manifold Hamiltonian Monte Carlo: Exploiting Sparsity for Fast Sampling of High-dimensional Targets [article]

Tore Selland Kleppe
<span title="2017-05-16">2017</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
To this end, a symmetric positive definite scaling matrix for RMHMC, which derives, via a modified Cholesky factorization, from the potentially indefinite negative Hessian of the target log-density is  ...  The methodology is able to exploit the sparsity of the Hessian, stemming from conditional independence modeling assumptions, and thus admit fast implementation of RMHMC even for high-dimensional target  ...  A further motivation for working with modified Cholesky factorizations, as opposed to say methods based on full spectral decompositions, is that this method can be implemented while exploiting sparsity  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1612.04093v2">arXiv:1612.04093v2</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/tgaq5oq3hbbvfcxz77nzqaqz5q">fatcat:tgaq5oq3hbbvfcxz77nzqaqz5q</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20191016164319/https://arxiv.org/pdf/1612.04093v2.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/19/68/1968a2541f10ed9b7041a7bc51563901892e0141.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1612.04093v2" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>

DeepCF: A Unified Framework of Representation Learning and Matching Function Learning in Recommender System [article]

Zhi-Hong Deng, Ling Huang, Chang-Dong Wang, Jian-Huang Lai, Philip S. Yu
<span title="2019-01-15">2019</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
To solve this problem, many methods have been studied, which can be generally categorized into two types, i.e., representation learning-based CF methods and matching function learning-based CF methods.  ...  Representation learning-based CF methods try to map users and items into a common representation space.  ...  Learning the Model A model-based method generally assumes that data can be generated by an underlying model asŷ ui = f (u, i|Θ), whereŷ ui denotes the prediction of y ui , i.e., the predicted probability  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1901.04704v1">arXiv:1901.04704v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/tbwqzkjoqfgt7ciidwathwcy5m">fatcat:tbwqzkjoqfgt7ciidwathwcy5m</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200824174526/https://arxiv.org/pdf/1901.04704v1.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/6c/57/6c57195829be6fbc5129ea89a1771a57681e2ef3.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1901.04704v1" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>

DeepCF: A Unified Framework of Representation Learning and Matching Function Learning in Recommender System

Zhi-Hong Deng, Ling Huang, Chang-Dong Wang, Jian-Huang Lai, Philip S. Yu
<span title="2019-07-17">2019</span> <i title="Association for the Advancement of Artificial Intelligence (AAAI)"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/wtjcymhabjantmdtuptkk62mlq" style="color: black;">PROCEEDINGS OF THE THIRTIETH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE AND THE TWENTY-EIGHTH INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE CONFERENCE</a> </i> &nbsp;
To solve this problem, many methods have been studied, which can be generally categorized into two types, i.e., representation learning-based CF methods and matching function learning-based CF methods.  ...  Representation learning-based CF methods try to map users and items into a common representation space.  ...  Learning the Model A model-based method generally assumes that data can be generated by an underlying model asŷ ui = f (u, i|Θ), whereŷ ui denotes the prediction of y ui , i.e., the predicted probability  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1609/aaai.v33i01.330161">doi:10.1609/aaai.v33i01.330161</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/wgz74gy6unb2rfjojl4fwvgj5u">fatcat:wgz74gy6unb2rfjojl4fwvgj5u</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200306060946/https://aaai.org/ojs/index.php/AAAI/article/download/3769/3647" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/9d/2d/9d2d605c57a2edba1808f8943aa6d520e4724ed2.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1609/aaai.v33i01.330161"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> Publisher / doi.org </button> </a>

Synthesizing Human Faces using Latent Space Factorization and Local Weights (Extended Version) [article]

Minyoung Kim, Young J. Kim
<span title="2021-07-19">2021</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
In addition, local weights generated by non-negative matrix factorization are applied to the factorized latent space so that the decomposed part space is semantically meaningful.  ...  We propose a 3D face generative model with local weights to increase the model's variations and expressiveness.  ...  Among those methods, non-negative matrix factorization (NMF) is a robust feature factorization method to represent data as part-based ones.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2107.08737v1">arXiv:2107.08737v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/zy7je4tiwvefxluqk2cbbdnwii">fatcat:zy7je4tiwvefxluqk2cbbdnwii</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20210721195139/https://arxiv.org/pdf/2107.08737v1.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/df/51/df51fe1f73ab5899ae36edc50a0c2330aa23098b.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2107.08737v1" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>

Dynamic organization of flocking behaviors in a large-scale boids model

Norihiro Maruyama, Daichi Saito, Yasuhiro Hashimoto, Takashi Ikegami
<span title="2019-03-11">2019</span> <i title="Springer Nature"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/o4fz62ei75gqfkwgqowe63uzte" style="color: black;">Journal of Computational Social Science</a> </i> &nbsp;
To define individual flocks and to capture their dynamic features, we applied a DBSCAN and a non-negative matrix factorization (NMF) to the boid dataset.  ...  A simulation of a half-million flock is studied using a simple boids model originally proposed by Craig Reynolds. It was modeled with a differential equation in 3D space with a periodic boundary.  ...  partially supported by the JSPS KAKENHI project A "Organization and Realization of Collective Intelligence Based on the Ethological and Life-Theoretical Investigations" (17H01249).  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1007/s42001-019-00037-9">doi:10.1007/s42001-019-00037-9</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/54cpby5i5ng43g2ijduzl4clpq">fatcat:54cpby5i5ng43g2ijduzl4clpq</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20190503032416/https://link.springer.com/content/pdf/10.1007%2Fs42001-019-00037-9.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/e7/30/e730382a613e2917a2ba571092bd212c0ba84cb5.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1007/s42001-019-00037-9"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> springer.com </button> </a>

Fast and accurate simulation of particle detectors using generative adversarial networks [article]

Pasquale Musella, Francesco Pandolfi
<span title="2018-05-02">2018</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
Deep generative models parametrised by neural networks have recently started to provide accurate results in modelling natural images.  ...  In particular, generative adversarial networks provide an unsupervised solution to this problem.  ...  We strongly support this initiative and believe that it will be crucial to spark developments of new algorithms from which the HEP community as a whole can profit. We thank Dr. M. DonegÃă, Prof. G.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1805.00850v1">arXiv:1805.00850v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/z7lwjj4cw5aldip2253sf765vy">fatcat:z7lwjj4cw5aldip2253sf765vy</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200827104908/https://arxiv.org/pdf/1805.00850v1.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/e6/4c/e64cbaaa90b0175a52c76a6427b0794aa922eea0.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1805.00850v1" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>

Hidden Markov Models Applied To Intraday Momentum Trading With Side Information [article]

Hugh Christensen, Simon Godsill, Richard Turner
<span title="2020-06-15">2020</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
A Hidden Markov Model for intraday momentum trading is presented which specifies a latent momentum state responsible for generating the observed securities' noisy returns.  ...  The number of latent states in the model is estimated using three techniques, cross validation, penalized likelihood criteria and simulation-based model selection for the marginal likelihood.  ...  An HMM for Trading Momentum Our model is based on the concept of a noisy trend, where the trend is a latent state and the price series is Brownian with a stochastic drift.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2006.08307v1">arXiv:2006.08307v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/slrxvdvnibfapdu3ufapty6rse">fatcat:slrxvdvnibfapdu3ufapty6rse</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200626153846/https://arxiv.org/pdf/2006.08307v1.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/e4/a5/e4a59a589fb7b07d1489c0f2ec90b3038c8e2ea4.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2006.08307v1" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>

Variational inference of latent state sequences using Recurrent Networks [article]

Justin Bayer, Christian Osendorfer
<span title="2014-09-30">2014</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
The proposed methods i) can infer distributed latent state-space trajectories with nonlinear transitions, ii) scale to large data sets thanks to the use of a stochastic objective and fast, approximate  ...  The use of independent Wiener processes as priors on the latent state sequence is a viable compromise between efficient computation of the Kullback-Leibler divergence from the variational approximation  ...  This work bases heavily on Theano [?].  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1406.1655v2">arXiv:1406.1655v2</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/dj4emg5bmbbnxfsueyojc3ka44">fatcat:dj4emg5bmbbnxfsueyojc3ka44</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200930105525/https://arxiv.org/pdf/1406.1655v1.pdf" title="fulltext PDF download [not primary version]" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <span style="color: #f43e3e;">&#10033;</span> <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/59/6d/596d52400e677584ba585c715ae2f138397f9ba4.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1406.1655v2" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>

Sensitivity of Gravity Wave Fluxes to Interannual Variations in Tropical Convection and Zonal Wind

M. Joan Alexander, David A. Ortland, Alison W. Grimsdell, Ji-Eun Kim
<span title="">2017</span> <i title="American Meteorological Society"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/52zwklo3cjcbpp3ocf6docuwwq" style="color: black;">Journal of the Atmospheric Sciences</a> </i> &nbsp;
The model generates a broad spectrum of tropical waves including planetary-  ...  Using an idealized model framework with high-frequency tropical latent heating variability derived from global satellite observations of precipitation and clouds, we examine the properties and effects  ...  Stochastic non-orographic parame-403 terization methods that account for realistically intermittent amplitudes have been developed [de 404 la Cámara and Lott 2015], and implementation in a global model  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1175/jas-d-17-0044.1">doi:10.1175/jas-d-17-0044.1</a> <a target="_blank" rel="external noopener" href="https://www.ncbi.nlm.nih.gov/pubmed/29379219">pmid:29379219</a> <a target="_blank" rel="external noopener" href="https://pubmed.ncbi.nlm.nih.gov/PMC5786383/">pmcid:PMC5786383</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/pk56njyr2rh67d367flqysca5a">fatcat:pk56njyr2rh67d367flqysca5a</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20190227045831/http://pdfs.semanticscholar.org/76f9/0734cc8dbfeb5a4e71dac3a818a528f43cf1.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/76/f9/76f90734cc8dbfeb5a4e71dac3a818a528f43cf1.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1175/jas-d-17-0044.1"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="unlock alternate icon" style="background-color: #fb971f;"></i> Publisher / doi.org </button> </a> <a target="_blank" rel="external noopener" href="https://www.ncbi.nlm.nih.gov/pmc/articles/PMC5786383" title="pubmed link"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> pubmed.gov </button> </a>

Discriminative conditional restricted Boltzmann machine for discrete choice and latent variable modelling

Melvin Wong, Bilal Farooq, Guillaume-Alexandre Bilodeau
<span title="">2017</span> <i title="Elsevier BV"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/7kzi6snz3vgupohajvdhnoo26i" style="color: black;">Journal of Choice Modeling</a> </i> &nbsp;
In this study, we explore the use of generative non-parametric modelling methods to estimate latent variables from prior choice distribution without the conventional use of measurement indicators.  ...  Our findings show that through non-parametric statistical tests, we can extract useful latent information on the behaviour of latent constructs through machine learning methods and present strong and significant  ...  A number of parametric and non-parametric modelling methods are available. Parametric models are regression based and random utility maximization structural models.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1016/j.jocm.2017.11.003">doi:10.1016/j.jocm.2017.11.003</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/wkp3k7s4lzarhht6tcjcbmbed4">fatcat:wkp3k7s4lzarhht6tcjcbmbed4</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200916202032/https://arxiv.org/pdf/1706.00505v1.pdf" title="fulltext PDF download [not primary version]" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <span style="color: #f43e3e;">&#10033;</span> <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/76/69/7669378380bceb52bea3e15d49baf0a70294ab5e.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1016/j.jocm.2017.11.003"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="unlock alternate icon" style="background-color: #fb971f;"></i> elsevier.com </button> </a>

Semi-Amortized Variational Autoencoders [article]

Yoon Kim, Sam Wiseman, Andrew C. Miller, David Sontag, Alexander M. Rush
<span title="2018-07-23">2018</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
Crucially, the local SVI procedure is itself differentiable, so the inference network and generative model can be trained end-to-end with gradient-based optimization.  ...  This semi-amortized approach enables the use of rich generative models without experiencing the posterior-collapse phenomenon common in training VAEs for problems like text generation.  ...  For all experiments we utilize stochastic gradient descent with momentum on the negative ELBO.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1802.02550v7">arXiv:1802.02550v7</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/vd33e3wnczfk3id7w4zlbzk7mm">fatcat:vd33e3wnczfk3id7w4zlbzk7mm</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200914074016/https://arxiv.org/pdf/1802.02550v7.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/ec/35/ec351d2b947aa7979df5ffd38560ce026f7c202e.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1802.02550v7" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>

Discriminative Bayesian Filtering Lends Momentum to the Stochastic Newton Method for Minimizing Log-Convex Functions [article]

Michael C. Burkhart
<span title="2021-04-27">2021</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
We contextualize this optimization problem as sequential Bayesian inference on a latent state-space model with a discriminatively-specified observation process.  ...  We establish matrix-based conditions under which the effect of older observations diminishes over time, in a manner analogous to Polyak's heavy ball momentum.  ...  a latent state-space model Hessian of log g j , respectively.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2104.12949v1">arXiv:2104.12949v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/s2mxx4c7brcclof2m4233b5nxu">fatcat:s2mxx4c7brcclof2m4233b5nxu</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20210513160601/https://arxiv.org/pdf/2104.12949v1.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/68/10/68100da17d5723b5659e150b26e56dc14848b41b.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2104.12949v1" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>

A Constrained Coupled Matrix-Tensor Factorization for Learning Time-evolving and Emerging Topics [article]

Sanaz Bahargam, Evangelos E. Papalexakis
<span title="2018-06-30">2018</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
Our method is based on a novel formulation of Constrained Coupled Matrix-Tensor Factorization, which adopts constraints well-motivated for, and, as we demonstrate, are essential for high-quality topic  ...  Finally, our proposed method has implications for automatic curriculum design using the extracted topics, where the notion of the level of difficulty is necessary for the proper modeling of prerequisites  ...  A ≥ 0. Nonnegativity is an important feature of latent factors since many real world tensors have non-negative values and hidden components have a physical meaning only when non-negative.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1807.00122v1">arXiv:1807.00122v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/xfzuktesgbhbll6rmdwzox7cq4">fatcat:xfzuktesgbhbll6rmdwzox7cq4</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200828155641/https://arxiv.org/pdf/1807.00122v1.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/43/18/431894e3403d6bcfd1ad2d446c73e25e51f3f5d2.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1807.00122v1" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>
&laquo; Previous Showing results 1 &mdash; 15 out of 10,195 results