dai::LC Class Reference

Approximate inference algorithm "Loop Corrected Belief Propagation" [MoK07]. More...

#include <dai/lc.h>

Inheritance diagram for dai::LC:

dai::DAIAlg< GRM > dai::InfAlg

List of all members.

Public Member Functions

 LC ()
 Default constructor.
 LC (const FactorGraph &fg, const PropertySet &opts)
 Construct from FactorGraph fg and PropertySet opts.
General InfAlg interface
virtual LCclone () const
 Returns a pointer to a new, cloned copy of *this (i.e., virtual copy constructor).
virtual std::string identify () const
 Identifies itself for logging purposes.
virtual Factor belief (const Var &v) const
 Returns the (approximate) marginal probability distribution of a variable.
virtual Factor belief (const VarSet &) const
 Returns the (approximate) marginal probability distribution of a set of variables.
virtual Factor beliefV (size_t i) const
 Returns the (approximate) marginal probability distribution of the variable with index i.
virtual std::vector< Factorbeliefs () const
 Returns all beliefs (approximate marginal probability distributions) calculated by the algorithm.
virtual Real logZ () const
 Returns the logarithm of the (approximated) partition sum (normalizing constant of the factor graph).
virtual void init ()
 Initializes all data structures of the approximate inference algorithm.
virtual void init (const VarSet &)
 Initializes all data structures corresponding to some set of variables.
virtual Real run ()
 Runs the approximate inference algorithm.
virtual Real maxDiff () const
 Returns maximum difference between single variable beliefs in the last iteration.
virtual size_t Iterations () const
 Returns number of iterations done (one iteration passes over the complete factorgraph).
virtual void setMaxIter (size_t maxiter)
 Sets maximum number of iterations (one iteration passes over the complete factorgraph).
virtual void setProperties (const PropertySet &opts)
 Set parameters of this inference algorithm.
virtual PropertySet getProperties () const
 Returns parameters of this inference algorithm converted into a PropertySet.
virtual std::string printProperties () const
 Returns parameters of this inference algorithm formatted as a string in the format "[key1=val1,key2=val2,...,keyn=valn]".
Additional interface specific for LC
Real CalcCavityDist (size_t i, const std::string &name, const PropertySet &opts)
 Approximates the cavity distribution of variable i, using the inference algorithm name with parameters opts.
Real InitCavityDists (const std::string &name, const PropertySet &opts)
 Approximates all cavity distributions using inference algorithm name with parameters opts.
long SetCavityDists (std::vector< Factor > &Q)
 Sets approximate cavity distributions to Q.
Factor NewPancake (size_t i, size_t _I, bool &hasNaNs)
 Updates the belief of the Markov blanket of variable i based upon the information from its _I 'th neighboring factor.
void CalcBelief (size_t i)
 Calculates the belief of variable i.
const Factorpancake (size_t i) const
 Returns the belief of the Markov blanket of variable i (including the variable itself).
const Factorcavitydist (size_t i) const
 Returns the approximate cavity distribution for variable i.

Public Attributes

struct dai::LC::Properties props

Static Public Attributes

static const char * Name = "LC"
 Name of this inference algorithm.

Private Attributes

std::vector< Factor_pancakes
 Stores for each variable the approximate cavity distribution multiplied with the omitted factors.
std::vector< Factor_cavitydists
 Stores for each variable the approximate cavity distribution.
std::vector< std::vector
< Factor > > 
_phis
 _phis[i][_I] corresponds to $ \phi^{\setminus i}_I(x_{I \setminus i}) $ in the paper
std::vector< Factor_beliefs
 Single variable beliefs.
Real _maxdiff
 Maximum difference encountered so far.
size_t _iters
 Number of iterations needed.

Classes

struct  Properties
 Parameters for LC. More...


Detailed Description

Approximate inference algorithm "Loop Corrected Belief Propagation" [MoK07].

Constructor & Destructor Documentation

dai::LC::LC (  )  [inline]

Default constructor.

dai::LC::LC ( const FactorGraph fg,
const PropertySet opts 
)

Construct from FactorGraph fg and PropertySet opts.

Parameters:
fg Factor graph.
opts Parameters
See also:
Properties


Member Function Documentation

virtual LC* dai::LC::clone (  )  const [inline, virtual]

Returns a pointer to a new, cloned copy of *this (i.e., virtual copy constructor).

Implements dai::InfAlg.

string dai::LC::identify (  )  const [virtual]

Identifies itself for logging purposes.

Implements dai::InfAlg.

virtual Factor dai::LC::belief ( const Var v  )  const [inline, virtual]

Returns the (approximate) marginal probability distribution of a variable.

Note:
Before this method is called, run() should have been called.

Reimplemented from dai::InfAlg.

Factor dai::LC::belief ( const VarSet vs  )  const [virtual]

Returns the (approximate) marginal probability distribution of a set of variables.

Note:
Before this method is called, run() should have been called.
Exceptions:
NOT_IMPLEMENTED if not implemented/supported.
BELIEF_NOT_AVAILABLE if the requested belief cannot be calculated with this algorithm.

Implements dai::InfAlg.

virtual Factor dai::LC::beliefV ( size_t  i  )  const [inline, virtual]

Returns the (approximate) marginal probability distribution of the variable with index i.

For some approximate inference algorithms, using beliefV() is preferred to belief() for performance reasons.

Note:
Before this method is called, run() should have been called.

Reimplemented from dai::InfAlg.

virtual std::vector<Factor> dai::LC::beliefs (  )  const [inline, virtual]

Returns all beliefs (approximate marginal probability distributions) calculated by the algorithm.

Note:
Before this method is called, run() should have been called.

Implements dai::InfAlg.

virtual Real dai::LC::logZ (  )  const [inline, virtual]

Returns the logarithm of the (approximated) partition sum (normalizing constant of the factor graph).

Note:
Before this method is called, run() should have been called.
Exceptions:
NOT_IMPLEMENTED if not implemented/supported

Implements dai::InfAlg.

void dai::LC::init (  )  [virtual]

Initializes all data structures of the approximate inference algorithm.

Note:
This method should be called at least once before run() is called.

Implements dai::InfAlg.

virtual void dai::LC::init ( const VarSet vs  )  [inline, virtual]

Initializes all data structures corresponding to some set of variables.

This method can be used to do a partial initialization after a part of the factor graph has changed. Instead of initializing all data structures, it only initializes those involving the variables in vs.

Exceptions:
NOT_IMPLEMENTED if not implemented/supported

Implements dai::InfAlg.

Real dai::LC::run (  )  [virtual]

Runs the approximate inference algorithm.

Note:
Before run() is called the first time, init() should have been called.

Implements dai::InfAlg.

virtual Real dai::LC::maxDiff (  )  const [inline, virtual]

Returns maximum difference between single variable beliefs in the last iteration.

Exceptions:
NOT_IMPLEMENTED if not implemented/supported

Reimplemented from dai::InfAlg.

virtual size_t dai::LC::Iterations (  )  const [inline, virtual]

Returns number of iterations done (one iteration passes over the complete factorgraph).

Exceptions:
NOT_IMPLEMENTED if not implemented/supported

Reimplemented from dai::InfAlg.

virtual void dai::LC::setMaxIter ( size_t   )  [inline, virtual]

Sets maximum number of iterations (one iteration passes over the complete factorgraph).

Exceptions:
NOT_IMPLEMENTED if not implemented/supported

Reimplemented from dai::InfAlg.

void dai::LC::setProperties ( const PropertySet opts  )  [virtual]

Set parameters of this inference algorithm.

The parameters are set according to the PropertySet opts. The values can be stored either as std::string or as the type of the corresponding MF::props member.

Implements dai::InfAlg.

PropertySet dai::LC::getProperties (  )  const [virtual]

Returns parameters of this inference algorithm converted into a PropertySet.

Implements dai::InfAlg.

string dai::LC::printProperties (  )  const [virtual]

Returns parameters of this inference algorithm formatted as a string in the format "[key1=val1,key2=val2,...,keyn=valn]".

Implements dai::InfAlg.

Real dai::LC::CalcCavityDist ( size_t  i,
const std::string &  name,
const PropertySet opts 
)

Approximates the cavity distribution of variable i, using the inference algorithm name with parameters opts.

Real dai::LC::InitCavityDists ( const std::string &  name,
const PropertySet opts 
)

Approximates all cavity distributions using inference algorithm name with parameters opts.

long dai::LC::SetCavityDists ( std::vector< Factor > &  Q  ) 

Sets approximate cavity distributions to Q.

Factor dai::LC::NewPancake ( size_t  i,
size_t  _I,
bool &  hasNaNs 
)

Updates the belief of the Markov blanket of variable i based upon the information from its _I 'th neighboring factor.

void dai::LC::CalcBelief ( size_t  i  ) 

Calculates the belief of variable i.

const Factor& dai::LC::pancake ( size_t  i  )  const [inline]

Returns the belief of the Markov blanket of variable i (including the variable itself).

const Factor& dai::LC::cavitydist ( size_t  i  )  const [inline]

Returns the approximate cavity distribution for variable i.


Member Data Documentation

std::vector<Factor> dai::LC::_pancakes [private]

Stores for each variable the approximate cavity distribution multiplied with the omitted factors.

std::vector<Factor> dai::LC::_cavitydists [private]

Stores for each variable the approximate cavity distribution.

std::vector<std::vector<Factor> > dai::LC::_phis [private]

_phis[i][_I] corresponds to $ \phi^{\setminus i}_I(x_{I \setminus i}) $ in the paper

std::vector<Factor> dai::LC::_beliefs [private]

Single variable beliefs.

Maximum difference encountered so far.

size_t dai::LC::_iters [private]

Number of iterations needed.

const char * dai::LC::Name = "LC" [static]

Name of this inference algorithm.


The documentation for this class was generated from the following files:

Generated on Thu Aug 5 19:04:07 2010 for libDAI by  doxygen 1.5.5