The Internet Archive has a preservation copy of this work in our general collections.
The file type is application/pdf.
Filters
Convex Relaxations for Learning Bounded Treewidth Decomposable Graphs
[article]
2012
arXiv
pre-print
Preserved Fulltext
We consider the problem of learning the structure of undirected graphical models with bounded treewidth, within the maximum likelihood framework. ...
A supergradient method is used to solve the dual problem, with a run-time complexity of O(k^3 n^k+2 n) for each iteration, where n is the number of variables and k is a bound on the treewidth. ...
We would also like to thank other members of the SIERRA and WILLOW project-teams for helpful discussions. ...
arXiv:1212.2573v1
fatcat:s7h5odxm6bd6hncumavdiypat4
Maximizing submodular functions using probabilistic graphical models
[article]
2013
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
These upper bounds may then be jointly maximized with respect to a set, while minimized with respect to the graph, leading to a convex variational inference scheme for maximizing submodular functions, ...
By considering graphs of increasing treewidths, we may then explore the trade-off between computational complexity and tightness of the relaxation. ...
We would also like to thank Nino Shervashidze for detailed feedback on the draft. ...
arXiv:1309.2593v1
fatcat:x4ckgjwbnnehfl7ypcgvmzl4ni
An Upper Bound on the Global Optimum in Parameter Estimation
2015
Conference on Uncertainty in Artificial Intelligence
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2022; you can also visit the original URL.
The file type is application/pdf.
Learning graphical model parameters from incomplete data is a non-convex optimization problem. ...
We exploit variables that are always observed in the dataset to get an upper bound on the global optimum which can give insight into the quality of the parameters learned by estimation algorithms. ...
By relaxing these equality constraints, we obtain a convex optimization problem that provides an upper bound on the original optimization problem. ...
dblp:conf/uai/RefaatD15
fatcat:7xgteqyfhncv7fx6g5mjt7wzoi
CRVI: Convex Relaxation for Variational Inference
2018
International Conference on Machine Learning
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2022; you can also visit the original URL.
The file type is application/pdf.
For most models, this optimization is highly non-convex and so hard to solve. ...
Our theoretical results guarantee very tight relaxation bounds that get nearer to the global optimal solution than traditional coordinate ascent. ...
In fact, it is upper bounded by a property of a defined graph structure for the original problem which is its treewidth. ...
dblp:conf/icml/FazelniaP18
fatcat:awd6e6s5gvb4hlc5b7bcjj5lii
Virtual Network Embedding via Decomposable LP Formulations: Orientations of Small Extraction Width and Beyond
[article]
2018
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
It therefore combines positive traits of heuristics and exact approaches: The runtime is polynomial for instances with bounded EW, and the algorithm returns approximate solutions with high probability. ...
This algorithm is based on a LP formulation and is FPT in the newly introduced graph parameter extraction width (EW). ...
] , stating that such problems can be decided in linear time for graphs with bounded treewidth. ...
arXiv:1810.11280v1
fatcat:hhivy7ktsjflbcqze4s764eary
New Limits of Treewidth-based tractability in Optimization
[article]
2019
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
Other Versions
This parameter has been used for decades for analyzing the complexity of various optimization problems and for obtaining tractable algorithms for problems where this parameter is bounded. ...
An example of this type of structure is given by treewidth: a graph theoretical parameter that measures how "tree-like" a graph is. ...
Acknowledgements Research reported in this paper was partially supported by NSF CAREER award CMMI-1452463 and by the Institute for Data Valorisation (IVADO). ...
arXiv:1807.02551v4
fatcat:xc5pqufrvbhe5frrehjaaquu5u
Large Margin Boltzmann Machines and Large Margin Sigmoid Belief Networks
[article]
2010
arXiv
pre-print
Preserved Fulltext
The Internet Archive has a preservation copy of this work in our general collections.
The file type is application/pdf.
This probability is data-distribution dependent and is maximized in learning. ...
LMSBNs in particular allow a very fast inference algorithm for arbitrary graph structures that runs in polynomial time with a high probability. ...
We implement a convex relaxation-based linear programming algorithm for inference, since in both (Finley and Joachims, 2008) and (Kulesza and Pereira, 2007) , the convex relaxation-based approximate ...
arXiv:1003.4781v1
fatcat:uwhwzd4jijasbk6duxyqzmvnre
Conditions beyond treewidth for tightness of higher-order LP relaxations
2017
International Conference on Artificial Intelligence and Statistics
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2022; you can also visit the original URL.
The file type is application/pdf.
Our results include showing that for higher order LP relaxations, treewidth is not precisely the right way to characterize tightness. ...
We consider binary pairwise models and introduce new methods which allow us to demonstrate refined conditions for tightness of LP relaxations in the Sherali-Adams hierarchy. ...
MR acknowledges support by the UK Engineering and Physical Sciences Research Council (EPSRC) grant EP/L016516/1 for the University of Cambridge Centre for Doctoral Training, the Cambridge Centre for Analysis ...
dblp:conf/aistats/RowlandPW17
fatcat:hvvaq55kxzakrjxjkzjpcywmrq
Marginal likelihoods for distributed estimation of graphical model parameters
2013
2013 5th IEEE International Workshop on Computational Advances in Multi-Sensor Adaptive Processing (CAMSAP)
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2015; you can also visit the original URL.
The file type is application/pdf.
Each node independently estimates local parameters through solving a low-dimensional convex optimization with data collected from its local neighborhood. ...
We then describe an alternative framework for distributed parameter estimation based on maximizing marginal likelihoods. ...
The bound for the twohop relaxed MML estimator approximates the bound for the GML estimator closely, which indicates its statistical efficiency. ...
doi:10.1109/camsap.2013.6714010
dblp:conf/camsap/MengWHW13
fatcat:uldjp7ut4rcmjcpokpqthzcg7m
Principled Deep Neural Network Training through Linear Programming
[article]
2022
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2022; you can also visit the original URL.
The file type is application/pdf.
Other Versions
Deep learning has received much attention lately due to the impressive empirical performance achieved by training algorithms. ...
Consequently, a need for a better theoretical understanding of these problems has become more evident in recent years. ...
linear regions of a Deep Neural Network [31] , performing inference [2] and providing strong convex relaxations for trained neural networks [3] . ...
arXiv:1810.03218v3
fatcat:xz2i3536h5grpmbzdum4esd5qu
Approximation Bounds for Inference using Cooperative Cuts
2011
International Conference on Machine Learning
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2022; you can also visit the original URL.
The file type is application/pdf.
This family includes models having arbitrary treewidth and arbitrary sized factors. ...
We thank Jens Vygen for the example of a very hard subadditive function. ...
For the relaxation, we need to extend f from a set function to a function on a continuous domain. ...
dblp:conf/icml/JegelkaB11a
fatcat:f4japnnemjd6xmpektyxa2y2uq
The Linear Programming Polytope of Binary Constraint Problems with Bounded Tree-Width
[chapter]
2007
Lecture Notes in Computer Science
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2019; you can also visit the original URL.
The file type is application/pdf.
when the BCP that is given has bounded tree-width. ...
However, the way we post the constraints is quite different so that it suffices to add variables for subsets of size equal to k only. ...
Another example are search algorithms that exploit problem decomposability, such as polynomial-time algorithms for problems on graphs with bounded tree-width [15] . ...
doi:10.1007/978-3-540-72397-4_20
fatcat:h2vpgpfqw5apxbwzugpkmie3um
Merging Strategies for Sum-Product Networks: From Trees to Graphs
2016
Conference on Uncertainty in Artificial Intelligence
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2022; you can also visit the original URL.
The file type is application/pdf.
cost of slight increase in the learning time. ...
Although, algorithms for inducing their structure from data have come quite far and often outperform algorithms that induce probabilistic graphical models, a key issue with existing approaches is that ...
Acknowledgements This research was funded in part by the DARPA Probabilistic Programming for Advanced Machine Learning Program under AFRL prime contract number FA8750-14-C-0005 and by the NSF award 1528037 ...
dblp:conf/uai/RahmanG16
fatcat:r6i2cksn25ed3g5b6fsr44gpsy
Tractability in constraint satisfaction problems: a survey
2015
Constraints
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2018; you can also visit the original URL.
The file type is application/pdf.
Acknowledgments We are grateful to Peter Jeavons and StanislavŽivný for their detailed comments on a first draft of this paper, and to the reviewers for their constructive comments. ...
It is well known that the class of instances whose constraint graph has bounded treewidth is tractable [85] . ...
(Graphs with treewidth bounded by k are also known as partial k-trees, because they are exactly the subgraphs of k-trees [4] ). ...
doi:10.1007/s10601-015-9198-6
fatcat:fl7kxmceh5bqzpyd2c37rtohii
Sidestepping Intractable Inference with Structured Ensemble Cascades
2010
Neural Information Processing Systems
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2022; you can also visit the original URL.
The file type is application/pdf.
Our framework jointly estimates parameters for all models in the ensemble for each level of the cascade by minimizing a novel, convex loss function, yet requires only a linear increase in computation over ...
learning or inference in a single tractable sub-model. ...
for low-treewidth models [4] . ...
dblp:conf/nips/WeissST10
fatcat:2z2xx6mzfza4lnkcl73q5dnoo4
« Previous
Showing results 1 — 15 out of 141 results