9,836 Hits in 1.7 sec

Population Quasi-Monte Carlo [article]

Chaofan Huang, V. Roshan Joseph, Simon Mak
2020 arXiv   pre-print
Mak {ξ i } n i=1 ∈ arg min x 1 ,...,xn∈{ym} M m=1Ê {(y m ,w m )} M m=1 , {x i } n i=1 = arg min x 1 ,...  ...  Definition 1 . 1 (Support Points; Mak and Joseph 2018) Let Y ∼ F where F is a target distribution function on ∅ = X ⊆ R p with finite means.  ... 
arXiv:2012.13769v1 fatcat:kyfg5lbswrb2jfn4ctpqi2eb4m

Distributional Clustering: A distribution-preserving clustering method [article]

Arvind Krishna, Simon Mak, Roshan Joseph
2019 arXiv   pre-print
A similar approach was used by Mak & Joseph (2018) for the case of k large, but for a different goal of experimental design.  ...  distributional clustering preserve the overall data distribution, it does not necessarily preserve marginal distributions over each variable -a property shown to be important for high-dimensional data reduction (Mak  ... 
arXiv:1911.05940v1 fatcat:nfznipkbyrbujh6rknipkchmee

Correspondence Learning via Linearly-invariant Embedding [article]

Riccardo Marin, Marie-Julie Rakotosaona, Simone Melzi, Maks Ovsjanikov
2020 arXiv   pre-print
In this paper, we propose a fully differentiable pipeline for estimating accurate dense correspondences between 3D point clouds. The proposed pipeline is an extension and a generalization of the functional maps framework. However, instead of using the Laplace-Beltrami eigenfunctions as done in virtually all previous works in this domain, we demonstrate that learning the basis from data can both improve robustness and lead to better accuracy in challenging settings. We interpret the basis as a
more » ... arned embedding into a higher dimensional space. Following the functional map paradigm the optimal transformation in this embedding space must be linear and we propose a separate architecture aimed at estimating the transformation by learning optimal descriptor functions. This leads to the first end-to-end trainable functional map-based correspondence approach in which both the basis and the descriptors are learned from data. Interestingly, we also observe that learning a canonical embedding leads to worse results, suggesting that leaving an extra linear degree of freedom to the embedding network gives it more robustness, thereby also shedding light onto the success of previous methods. Finally, we demonstrate that our approach achieves state-of-the-art results in challenging non-rigid 3D point cloud correspondence applications.
arXiv:2010.13136v1 fatcat:fxzmkh3bo5cjvjmpvqf6hl3su4

Why you should learn functional basis [article]

Riccardo Marin, Souhaib Attaiki, Simone Melzi, Emanuele Rodolà, Maks Ovsjanikov
2021 arXiv   pre-print
Zoomout: [39] Jing Ren, Simone Melzi, Maks Ovsjanikov, and Peter Spectral upsampling for efficient shape correspondence. Wonka.  ...  In International Conference on 3D Vi- [26] Simone Melzi, Jing Ren, Emanuele Rodolà, Abhishek sion (3DV), 2019. 9 Sharma, Peter Wonka, and Maks Ovsjanikov.  ... 
arXiv:2112.07289v1 fatcat:yvrigbygibelrdbm7tr6xmqkoa

Gaussian Process Subspace Regression for Model Reduction [article]

Ruda Zhang and Simon Mak and David Dunson
2021 arXiv   pre-print
arXiv:2107.04668v1 fatcat:hnpvdwacn5b27mzmqluqfyzt7q

Gagnon et Simon et la théorie des scripts sexuels

Maks Banens
2010 La psychologie vue par… les sciences humaines  
Maks BANENS MoDyS -Lyon 2 Notes 1.  ...  et l a théori e des scri pts sexuel s Maks BANENS  ... 
doi:10.35562/canalpsy.415 fatcat:rqxxhjtd7bgd5gs6kx7on7dcje

Imaging of congenital chest wall deformities

Sze M Mak, Basrull N Bhaludin, Sahar Naaseri, Francesco Di Chiara, Simon Jordan, Simon Padley
2016 British Journal of Radiology  
To identify the anatomy and pathology of chest wall malformations presenting for consideration for corrective surgery or as a possible chest wall "mass", and to review the common corrective surgical procedures. Congenital chest wall deformities are caused by anomalies of chest wall growth, leading to sternal depression or protrusion, or are related to failure of normal spine or rib development. Cross-sectional imaging allows appreciation not only of the involved structures but also assessment
more » ... the degree of displacement or deformity of adjacent but otherwise normal structures and differentiation between anatomical deformity and neoplasia. In some cases, CT is also useful for surgical planning. The use of three-dimensional reconstructions, utilizing a low-dose technique, provides important information for the surgeon to discuss the nature of anatomical abnormalities and planned corrections with the patient and often with their parents. In this pictorial essay, we discuss the radiological features of the commonest congenital chest wall deformities and illustrate pre-and post-surgical appearances for those undergoing surgical correction.
doi:10.1259/bjr.20150595 pmid:26916279 pmcid:PMC4985446 fatcat:gh6a7z2pc5fcjmtbmboyxh4ste

BdryGP: a new Gaussian process model for incorporating boundary information [article]

Liang Ding, Simon Mak, C. F. Jeff Wu
2019 arXiv   pre-print
Gaussian processes (GPs) are widely used as surrogate models for emulating computer code, which simulate complex physical phenomena. In many problems, additional boundary information (i.e., the behavior of the phenomena along input boundaries) is known beforehand, either from governing physics or scientific knowledge. While there has been recent work on incorporating boundary information within GPs, such models do not provide theoretical insights on improved convergence rates. To this end, we
more » ... opose a new GP model, called BdryGP, for incorporating boundary information. We show that BdryGP not only has improved convergence rates over existing GP models (which do not incorporate boundaries), but is also more resistant to the "curse-of-dimensionality" in nonparametric regression. Our proofs make use of a novel connection between GP interpolation and finite-element modeling.
arXiv:1908.08868v1 fatcat:tdz7cveykzecng7ufgwdwfsd3e

A regional compound Poisson process for hurricane and tropical storm damage [article]

Simon Mak, Derek Bingham, Yi Lu
2016 arXiv   pre-print
In light of intense hurricane activity along the U.S. Atlantic coast, attention has turned to understanding both the economic impact and behaviour of these storms. The compound Poisson-lognormal process has been proposed as a model for aggregate storm damage, but does not shed light on regional analysis since storm path data are not used. In this paper, we propose a fully Bayesian regional prediction model which uses conditional autoregressive (CAR) models to account for both storm paths and
more » ... tial patterns for storm damage. When fitted to historical data, the analysis from our model both confirms previous findings and reveals new insights on regional storm tendencies. Posterior predictive samples can also be used for pricing regional insurance premiums, which we illustrate using three different risk measures.
arXiv:1602.03940v1 fatcat:cg5dnalghnhu3ipexrzoiss5au

Uncertainty Quantification for Inferring Hawkes Networks [article]

Haoyun Wang, Liyan Xie, Alex Cuozzo, Simon Mak, Yao Xie
2020 arXiv   pre-print
Multivariate Hawkes processes are commonly used to model streaming networked event data in a wide variety of applications. However, it remains a challenge to extract reliable inference from complex datasets with uncertainty quantification. Aiming towards this, we develop a statistical inference framework to learn causal relationships between nodes from networked data, where the underlying directed graph implies Granger causality. We provide uncertainty quantification for the maximum likelihood
more » ... stimate of the network multivariate Hawkes process by providing a non-asymptotic confidence set. The main technique is based on the concentration inequalities of continuous-time martingales. We compare our method to the previously-derived asymptotic Hawkes process confidence interval, and demonstrate the strengths of our method in an application to neuronal connectivity reconstruction.
arXiv:2006.07506v2 fatcat:hlp3dor34nciznlq2ozyvejzu4

Uptake of NO3on soot and pyrene surfaces

Jackson Mak, Simone Gross, Allan K. Bertram
2007 Geophysical Research Letters  
1] The reaction of NO 3 with methane soot, hexane soot, and solid pyrene was investigated using a flow tube reactor. The uptake of NO 3 on fresh soot was fast (uptake coefficient >0.1). Based on this result and an assumed density of reactive sites on soot, the time to process or oxidize 90% of a soot surface in the atmosphere would take only approximately five minutes. This suggests that NO 3 chemistry can rapidly oxidize soot surfaces under atmospheric conditions. After exposing soot films to
more » ... O 3 for approximately 180 minutes in the laboratory, the uptake reaches a steady-state value. The steady state uptake coefficients (assuming a geometric surface area) were 0.0054 ± 0.0027 and 0.0025 ± 0.0018 for methane and hexane soot, respectively. These numbers are used to show that heterogeneous reactions between NO 3 and soot are not likely a significant sink of gas-phase NO 3 under most atmospheric conditions. The uptake of NO 3 on fresh pyrene surfaces was also fast (uptake coefficient >0.1), and much faster than previously suggested. We argue that under certain atmospheric conditions reactions between NO 3 and surface-bound polycyclic aromatic hydrocarbons (PAHs) may be an important loss process of PAHs in the atmosphere.
doi:10.1029/2007gl029756 fatcat:qdnc3o6a2rcpdf5avx3yi6q7u4

Structural covariance networks in children with autism or ADHD [article]

Richard A.I. Bethlehem, Rafael Romero-Garcia, Elijah Mak, Edward Bullmore, Simon Baron-Cohen
2017 bioRxiv   pre-print
While autism and ADHD are considered distinct conditions from a diagnostic perspective, they share some phenotypic features and have high comorbidity. Taking a dual-condition approach might help elucidate shared and distinct neural characteristics. Graph theory was used to analyse properties of cortical thickness structural covariance networks across both conditions and relative to a neurotypical (NT; n=87) group using data from the ABIDE (autism; n=62) and ADHD-200 datasets (ADHD; n=69). This
more » ... as analysed in a theoretical framework examining potential differences in long and short range connectivity. We found convergence between autism and ADHD, where both conditions show an overall decrease in CT covariance with increased Euclidean distance compared to a neurotypical population. The two conditions also show divergence: less modular overlap between the two conditions than there is between each condition and the neurotypical group. Lastly, the ADHD group also showed reduced wiring costs compared to the autism groups. Our results indicate a need for taking an integrated approach when considering highly comorbid conditions such as autism and ADHD. Both groups show a distance-covariance relation that more strongly favours short-range over long-range. Thus, on some network features the groups seem to converge, yet on others there is divergence.
doi:10.1101/110643 fatcat:u7dhfsuxu5h7lflkc7h5xo3yn4

PERCEPT: a new online change-point detection method using topological data analysis [article]

Xiaojun Zheng, Simon Mak, Liyan Xie, Yao Xie
2022 arXiv   pre-print
., , 2022) ) and complex physical systems (Mak et al., 2018) .  ... 
arXiv:2203.04246v1 fatcat:cdgkwpu4qvfgllb74cfgybaw7q

Adaptive Approximation for Multivariate Linear Problems with Inputs Lying in a Cone [article]

Yuhan Ding, Fred J. Hickernell, Peter Kritzer, Simon Mak
2019 arXiv   pre-print
We study adaptive approximation algorithms for general multivariate linear problems where the sets of input functions are non-convex cones. While it is known that adaptive algorithms perform essentially no better than non-adaptive algorithms for convex input sets, the situation may be different for non-convex sets. A typical example considered here is function approximation based on series expansions. Given an error tolerance, we use series coefficients of the input to construct an approximate
more » ... olution such that the error does not exceed this tolerance. We study the situation where we can bound the norm of the input based on a pilot sample, and the situation where we keep track of the decay rate of the series coefficients of the input. Moreover, we consider situations where it makes sense to infer coordinate and smoothness importance. Besides performing an error analysis, we also study the information cost of our algorithms and the computational complexity of our problems, and we identify conditions under which we can avoid a curse of dimensionality.
arXiv:1903.10738v1 fatcat:dpbrwgxuyrcl7j6zgghmnt7yoq

Support points [article]

Simon Mak, V. Roshan Joseph
2018 arXiv   pre-print
arXiv:1609.01811v7 fatcat:a6no2smjyvdh7ln3te2i7lap64
« Previous Showing results 1 — 15 out of 9,836 results