var bibbase_data = {"data":"\n\n
\n\n \n\n \n\n \n\n \n \n\n \n\n\n\n
\n\n \n\n\n
\n \n\n Excellent! Next, you can embed this page using\n one of several \n options.\n
\n\n
\n \n\n

To the site owner:

\n\n

Action required! Mendeley is changing its\n API. In order to keep using Mendeley with BibBase past April\n 14th, you need to:\n

    \n
  1. renew the authorization for BibBase on Mendeley, and
  2. \n
  3. update the BibBase URL\n in your page the same way you did when you initially set up\n this page.
  4. \n

\n\n

\n \n \n Fix it now\n

\n
\n\n
\n\n\n
\n \n \n
\n
\n  \n 2017\n \n \n (1)\n \n \n
\n
\n \n \n
\n
\n  \n undefined\n \n \n (1)\n \n \n
\n
\n \n \n
\n
\n \n \n\n \n \n Lanusse, F.; Ma, Q.; Li, N.; Thomas, C.; Li, C.; Ravanbakhsh, S.; Mandelbaum, R.; and Poczos, B.\n \n\n\n \n \n \n CMU DeepLens: Deep Learning For Automatic Image-based Galaxy-Galaxy Strong Lens Finding.\n \n\n\n \n\n\n\n Preprint arXiv:1703.02642, . 2017.\n \n\n Winner of 2/4 categories in strong lens-finding competition!\n\n
\n\n\n \n \n \n \"CMU arxiv\n  \n \n \n \"CMU code\n  \n \n \n \"CMU in press\n  \n \n\n \n\n bibtex \n \n \n \n  \n \n abstract \n \n\n \n\n \n\n \n \n \n \n \n \n \n \n\n\n
\n
@article{francois_lensing,\n  title={CMU DeepLens: Deep Learning For Automatic Image-based Galaxy-Galaxy Strong Lens Finding},\n  author={Lanusse, Francois and Ma, Quanbin and Li, Nan and Collett Thomas and Li, Chun-Liang and Ravanbakhsh, Siamak and Mandelbaum, Rachel and Poczos, Barnabas},\n  url_Arxiv = {https://arxiv.org/abs/1703.02642},\n  journal={Preprint arXiv:1703.02642},\n  abstract={"Galaxy-scale strong gravitational lensing is not only a valuable probe of the dark matter distribution of massive galaxies, but can also provide valuable cosmological constraints, either by studying the population of strong lenses or by measuring time delays in lensed quasars. Due to the rarity of galaxy-scale strongly lensed systems, fast and reliable automated lens finding methods will be essential in the era of large surveys such as LSST, Euclid, and WFIRST. To tackle this challenge, we introduce CMU DeepLens, a new fully automated galaxy-galaxy lens finding method based on Deep Learning. This supervised machine learning approach does not require any tuning after the training step which only requires realistic image simulations of strongly lensed systems. We train and validate our model on a set of 20,000 LSST-like mock observations including a range of lensed systems of various sizes and signal-to-noise ratios (S/N). We find on our simulated data set that for a rejection rate of non-lenses of 99 percent, a completeness of 90 percent can be achieved for lenses with Einstein radii larger than 1.4" and S/N larger than 20 on individual g-band LSST exposures. Finally, we emphasize the importance of realistically complex simulations for training such machine learning methods by demonstrating that the performance of models of significantly different complexities cannot be distinguished on simpler simulations"},\nBibbase_Note={<font color="#E74C3C"> Winner of 2/4 categories in strong lens-finding competition!</font>},\n  year={2017},\n  url_code={https://github.com/McWilliamsCenter/CMUDeepLens},\nurl_in_press={http://www.cmu.edu/mcs/news-events/2017/0512-Strong-Lensing-Challenge.html},\n}\n\n
\n
\n\n\n
\n \"Galaxy-scale strong gravitational lensing is not only a valuable probe of the dark matter distribution of massive galaxies, but can also provide valuable cosmological constraints, either by studying the population of strong lenses or by measuring time delays in lensed quasars. Due to the rarity of galaxy-scale strongly lensed systems, fast and reliable automated lens finding methods will be essential in the era of large surveys such as LSST, Euclid, and WFIRST. To tackle this challenge, we introduce CMU DeepLens, a new fully automated galaxy-galaxy lens finding method based on Deep Learning. This supervised machine learning approach does not require any tuning after the training step which only requires realistic image simulations of strongly lensed systems. We train and validate our model on a set of 20,000 LSST-like mock observations including a range of lensed systems of various sizes and signal-to-noise ratios (S/N). We find on our simulated data set that for a rejection rate of non-lenses of 99 percent, a completeness of 90 percent can be achieved for lenses with Einstein radii larger than 1.4\" and S/N larger than 20 on individual g-band LSST exposures. Finally, we emphasize the importance of realistically complex simulations for training such machine learning methods by demonstrating that the performance of models of significantly different complexities cannot be distinguished on simpler simulations\"\n
\n\n\n
\n\n
\n\n\n\n\n
\n
\n\n\n\n\n
\n
\n\n
\n
\n  \n 2016\n \n \n (1)\n \n \n
\n
\n \n \n
\n
\n  \n undefined\n \n \n (1)\n \n \n
\n
\n \n \n
\n
\n \n \n\n \n \n Li, C.; Ravanbakhsh, S.; and Poczos, B.\n \n\n\n \n \n \n Annealing Gaussian into ReLU: a New Sampling Strategy for Leaky-ReLU RBM.\n \n\n\n \n\n\n\n Preprint arXiv:1611.03879, . 2016.\n \n\n\n\n
\n\n\n \n \n \n \"Annealing arxiv\n  \n \n\n \n\n bibtex \n \n \n \n  \n \n abstract \n \n\n \n\n \n\n \n \n \n \n \n \n \n \n\n\n
\n
@article{chunliang_relurbm,\n  title={Annealing Gaussian into ReLU: a New Sampling Strategy for Leaky-ReLU RBM},\n  author={Li, Chun-Liang and Ravanbakhsh, Siamak and Poczos, Barnabas},\n  journal={Preprint arXiv:1611.03879},\n  year={2016},\nurl_arXiv = {https://arxiv.org/abs/1611.03879},\nabstract = {"Restricted Boltzmann Machine (RBM) is a bipartite graphical model that is used\nas the building block in energy-based deep generative models. Due to numerical\nstability and quantifiability of the likelihood, RBM is commonly used with\nBernoulli units. Here, we consider an alternative member of exponential family\nRBM with leaky rectified linear units – called leaky RBM. We first study the joint\nand marginal distributions of leaky RBM under different leakiness, which provides\nus important insights by connecting the leaky RBM model and truncated\nGaussian distributions. The connection leads us to a simple yet efficient method\nfor sampling from this model, where the basic idea is to anneal the leakiness rather\nthan the energy; – i.e., start from a fully Gaussian/Linear unit and gradually decrease\nthe leakiness over iterations. This serves as an alternative to the annealing\nof the temperature parameter and enables numerical estimation of the likelihood\nthat are more efficient and more accurate than the commonly used annealed importance\nsampling (AIS). We further demonstrate that the proposed sampling algorithm\nenjoys faster mixing property than contrastive divergence algorithm, which\nbenefits the training without any additional computational cost."},\n}\n
\n
\n\n\n
\n \"Restricted Boltzmann Machine (RBM) is a bipartite graphical model that is used as the building block in energy-based deep generative models. Due to numerical stability and quantifiability of the likelihood, RBM is commonly used with Bernoulli units. Here, we consider an alternative member of exponential family RBM with leaky rectified linear units – called leaky RBM. We first study the joint and marginal distributions of leaky RBM under different leakiness, which provides us important insights by connecting the leaky RBM model and truncated Gaussian distributions. The connection leads us to a simple yet efficient method for sampling from this model, where the basic idea is to anneal the leakiness rather than the energy; – i.e., start from a fully Gaussian/Linear unit and gradually decrease the leakiness over iterations. This serves as an alternative to the annealing of the temperature parameter and enables numerical estimation of the likelihood that are more efficient and more accurate than the commonly used annealed importance sampling (AIS). We further demonstrate that the proposed sampling algorithm enjoys faster mixing property than contrastive divergence algorithm, which benefits the training without any additional computational cost.\"\n
\n\n\n
\n\n
\n\n\n\n\n
\n
\n\n\n\n\n
\n
\n\n
\n
\n  \n 2014\n \n \n (1)\n \n \n
\n
\n \n \n
\n
\n  \n undefined\n \n \n (1)\n \n \n
\n
\n \n \n
\n
\n \n \n\n \n \n Ravanbakhsh, S.; and Greiner, R.\n \n\n\n \n \n \n Revisiting algebra and complexity of inference in graphical models.\n \n\n\n \n\n\n\n arXiv preprint arXiv:1409.7410, . 2014.\n \n\n\n\n
\n\n\n \n \n \n \"Revisiting paper\n  \n \n\n \n\n bibtex \n \n \n \n  \n \n abstract \n \n\n \n\n \n\n \n \n \n \n \n \n \n \n\n\n
\n
@article{ravanbakhsh_algebra,\n  title={Revisiting algebra and complexity of inference in graphical models},\n  author={Ravanbakhsh, Siamak and Greiner, Russell},\n  journal={arXiv preprint arXiv:1409.7410},\n  year={2014},\nurl_Paper = {https://arxiv.org/pdf/1409.7410v4.pdf},\n  abstract={"This paper studies the form and complexity of inference in graphical models using the abstraction offered by algebraic structures. In particular, we broadly formalize inference problems in graphical models by viewing them as a sequence of operations based on commutative semigroups. We then study the computational complexity of inference by organizing various problems into an "inference hierarchy". When the underlying structure of an inference problem is a commutative semiring -- i.e. a combination of two commutative semigroups with the distributive law -- a message passing procedure called belief propagation can leverage this distributive law to perform polynomial-time inference for certain problems. After establishing the NP-hardness of inference in any commutative semiring, we investigate the relation between algebraic properties in this setting and further show that polynomial-time inference using distributive law does not (trivially) extend to inference problems that are expressed using more than two commutative semigroups. We then extend the algebraic treatment of message passing procedures to survey propagation, providing a novel perspective using a combination of two commutative semirings. This formulation generalizes the application of survey propagation to new settings."},\n}\n\n
\n
\n\n\n
\n \"This paper studies the form and complexity of inference in graphical models using the abstraction offered by algebraic structures. In particular, we broadly formalize inference problems in graphical models by viewing them as a sequence of operations based on commutative semigroups. We then study the computational complexity of inference by organizing various problems into an \"inference hierarchy\". When the underlying structure of an inference problem is a commutative semiring -- i.e. a combination of two commutative semigroups with the distributive law -- a message passing procedure called belief propagation can leverage this distributive law to perform polynomial-time inference for certain problems. After establishing the NP-hardness of inference in any commutative semiring, we investigate the relation between algebraic properties in this setting and further show that polynomial-time inference using distributive law does not (trivially) extend to inference problems that are expressed using more than two commutative semigroups. We then extend the algebraic treatment of message passing procedures to survey propagation, providing a novel perspective using a combination of two commutative semirings. This formulation generalizes the application of survey propagation to new settings.\"\n
\n\n\n
\n\n
\n\n\n\n\n
\n
\n\n\n\n\n
\n
\n\n\n\n\n
\n\n\n \n
\n
\n \n

Embedding in another Page

\n
\n
\n\n

\n Copy&paste any of the following snippets into an existing\n page to embed this page. For more details see the\n documention.\n

\n\n JavaScript\n (Easiest)\n
\n \n <script src=\"https://bibbase.org/show?bib=cs.ubc.ca%2F~siamakx%2Fpreprints.bib&jsonp=1&authorFirst=1&css=css/bibbase_css.css&group0=year&group1=order&jsonp=1\"></script>\n \n
\n\n PHP\n
\n \n <?php\n $contents = file_get_contents(\"https://bibbase.org/show?bib=cs.ubc.ca%2F~siamakx%2Fpreprints.bib&jsonp=1&authorFirst=1&css=css/bibbase_css.css&group0=year&group1=order\");\n print_r($contents);\n ?>\n \n
\n\n iFrame\n
\n \n <iframe src=\"https://bibbase.org/show?bib=cs.ubc.ca%2F~siamakx%2Fpreprints.bib&jsonp=1&authorFirst=1&css=css/bibbase_css.css&group0=year&group1=order\"></iframe>\n \n
\n\n \n
\n
\n \n
\n
\n\n \n \n \n \n\n
\n\n"}; document.write(bibbase_data.data);