case class DiscreteLowRankGaussianProcess[D, DDomain[DD] <: DiscreteDomain[DD], Value] extends DiscreteGaussianProcess[D, DDomain, Value] with Product with Serializable
Represents a low-rank gaussian process, that is only defined at a finite, discrete set of points. It supports the same operations as the LowRankGaussianProcess class, but always returns instead a discrete representation. Furthermore, most operations are much more efficient, as they are implemented using fast matrix/vector operations.
Where the modeled functions in a LowRankGaussianProcess are of type Point[D]=>Vector[D], this discretized version is of type VectorPointData.
It is possible to convert a DiscreteLowRankGaussianProcess to a LowRankGaussianProcess by calling the interpolation method.
- Self Type
- DiscreteLowRankGaussianProcess[D, DDomain, Value]
- See also
- Alphabetic
- By Inheritance
- DiscreteLowRankGaussianProcess
- Serializable
- Product
- Equals
- DiscreteGaussianProcess
- AnyRef
- Any
- Hide All
- Show All
- Public
- Protected
Value Members
- final def !=(arg0: Any): Boolean
- Definition Classes
- AnyRef → Any
- final def ##(): Int
- Definition Classes
- AnyRef → Any
- final def ==(arg0: Any): Boolean
- Definition Classes
- AnyRef → Any
- val _domain: DDomain[D]
- final def asInstanceOf[T0]: T0
- Definition Classes
- Any
- val basisMatrix: DenseMatrix[Double]
- def clone(): AnyRef
- Attributes
- protected[lang]
- Definition Classes
- AnyRef
- Annotations
- @throws(classOf[java.lang.CloneNotSupportedException]) @native()
- def coefficients(s: DiscreteField[D, DDomain, Value]): DenseVector[Double]
Discrete version of Vector[DO], Double)])
- val cov: DiscreteMatrixValuedPDKernel[D]
- Definition Classes
- DiscreteGaussianProcess
- val domain: DDomain[D]
- Definition Classes
- DiscreteGaussianProcess
- final def eq(arg0: AnyRef): Boolean
- Definition Classes
- AnyRef
- def finalize(): Unit
- Attributes
- protected[lang]
- Definition Classes
- AnyRef
- Annotations
- @throws(classOf[java.lang.Throwable])
- final def getClass(): Class[_ <: AnyRef]
- Definition Classes
- AnyRef → Any
- Annotations
- @native()
- def instance(c: DenseVector[Double]): DiscreteField[D, DDomain, Value]
Discrete version of DiscreteLowRankGaussianProcess.instance
- def instanceAtPoint(c: DenseVector[Double], pid: PointId): Value
Get instance at a specific point
- def instanceVector(alpha: DenseVector[Double]): DenseVector[Double]
- Attributes
- protected[statisticalmodel]
- def instanceVectorAtPoint(alpha: DenseVector[Double], pid: PointId): DenseVector[Double]
- Attributes
- protected[statisticalmodel]
- def interpolate(interpolator: FieldInterpolator[D, DDomain, Value]): LowRankGaussianProcess[D, Value]
Interpolates the gaussian process using the given interpolator.
Interpolates the gaussian process using the given interpolator. Interpolation is achieved by interoplating the mean and eigenfunctions using the given interpolator.
- interpolator
the interpolator used to interpolate the mean and eigenfunctions
- returns
a (continuous) low-rank Gaussian process
- Definition Classes
- DiscreteLowRankGaussianProcess → DiscreteGaussianProcess
- def interpolateNystrom(nNystromPoints: Int = 2 * rank)(implicit rand: Random): LowRankGaussianProcess[D, Value]
Interpolates discrete Gaussian process to have a new, continuous representation as a DiscreteLowRankGaussianProcess.
Interpolates discrete Gaussian process to have a new, continuous representation as a DiscreteLowRankGaussianProcess. This is achieved by using a Nystrom method for computing the kl basis. The mean function is currently interpolated using a nearest neighbor approach.
- nNystromPoints
determines how many points of the domain are used to estimate the full kl basis.
- final def isInstanceOf[T0]: Boolean
- Definition Classes
- Any
- def klBasis: KLBasis[D, DDomain, Value]
Returns the variance and associated basis function that defines the process.
Returns the variance and associated basis function that defines the process. The basis is the (discretized) Karhunen Loeve basis (e.g. it is obtained from a Mercer's decomposition of the covariance function
- def logpdf(instance: DiscreteField[D, DDomain, Value]): Double
Returns the log of the probability density of the instance
Returns the log of the probability density of the instance
If you are interested in ordinal comparisons of PDFs, use this as it is numerically more stable
- Definition Classes
- DiscreteLowRankGaussianProcess → DiscreteGaussianProcess
- def logpdf(coefficients: DenseVector[Double]): Double
Returns the log of the probability density of the instance produced by the x coefficients.
Returns the log of the probability density of the instance produced by the x coefficients.
If you are interested in ordinal comparisons of PDFs, use this as it is numerically more stable
- def marginal(pointIds: Seq[PointId])(implicit domainCreator: Create[D]): DiscreteLowRankGaussianProcess[D, UnstructuredPointsDomain, Value]
The marginal distribution for the points specified by the given point ids.
The marginal distribution for the points specified by the given point ids. Note that this is again a DiscreteGaussianProcess.
- Definition Classes
- DiscreteLowRankGaussianProcess → DiscreteGaussianProcess
- def marginal(pointId: PointId): MultivariateNormalDistribution
The marginal distribution at a given (single) point, specified by the pointId.
The marginal distribution at a given (single) point, specified by the pointId.
- Definition Classes
- DiscreteGaussianProcess
- val mean: DiscreteField[D, DDomain, Value]
- Definition Classes
- DiscreteGaussianProcess
- val meanVector: DenseVector[Double]
- final def ne(arg0: AnyRef): Boolean
- Definition Classes
- AnyRef
- final def notify(): Unit
- Definition Classes
- AnyRef
- Annotations
- @native()
- final def notifyAll(): Unit
- Definition Classes
- AnyRef
- Annotations
- @native()
- val outputDim: Int
- Definition Classes
- DiscreteGaussianProcess
- def pdf(instance: DiscreteField[D, DDomain, Value]): Double
Returns the probability density of the given instance
Returns the probability density of the given instance
- Definition Classes
- DiscreteLowRankGaussianProcess → DiscreteGaussianProcess
- def pdf(coefficients: DenseVector[Double]): Double
Returns the probability density of the instance produced by the x coefficients
- def posterior(trainingData: IndexedSeq[(PointId, Value, MultivariateNormalDistribution)]): DiscreteLowRankGaussianProcess[D, DDomain, Value]
Discrete version of Vector[DO], Double)]).
Discrete version of Vector[DO], Double)]). In contrast to this method, the points for the training data are defined by the pointId. The returned posterior process is defined at the same points.
- def posterior(trainingData: IndexedSeq[(PointId, Value)], sigma2: Double): DiscreteLowRankGaussianProcess[D, DDomain, Value]
Discrete version of Vector[DO])], sigma2: Double.
Discrete version of Vector[DO])], sigma2: Double. In contrast to this method, the points for the training data are defined by the pointId. The returned posterior process is defined at the same points.
- def productElementNames: Iterator[String]
- Definition Classes
- Product
- def project(s: DiscreteField[D, DDomain, Value]): DiscreteField[D, DDomain, Value]
Discrete version of Vector[DO])], Double)
Discrete version of Vector[DO])], Double)
- Definition Classes
- DiscreteLowRankGaussianProcess → DiscreteGaussianProcess
- val rank: Int
- def sample()(implicit random: Random): DiscreteField[D, DDomain, Value]
Discrete version of DiscreteLowRankGaussianProcess.sample
Discrete version of DiscreteLowRankGaussianProcess.sample
- Definition Classes
- DiscreteLowRankGaussianProcess → DiscreteGaussianProcess
- final def synchronized[T0](arg0: => T0): T0
- Definition Classes
- AnyRef
- def truncate(rank: Int): DiscreteLowRankGaussianProcess[D, DDomain, Value]
Returns a reduced rank model, using only the leading basis function of the Karhunen-loeve expansion.
- val variance: DenseVector[Double]
- implicit val vectorizer: Vectorizer[Value]
- Definition Classes
- DiscreteLowRankGaussianProcess → DiscreteGaussianProcess
- final def wait(): Unit
- Definition Classes
- AnyRef
- Annotations
- @throws(classOf[java.lang.InterruptedException])
- final def wait(arg0: Long, arg1: Int): Unit
- Definition Classes
- AnyRef
- Annotations
- @throws(classOf[java.lang.InterruptedException])
- final def wait(arg0: Long): Unit
- Definition Classes
- AnyRef
- Annotations
- @throws(classOf[java.lang.InterruptedException]) @native()
Deprecated Value Members
- def interpolateNearestNeighbor: LowRankGaussianProcess[D, Value]
Interpolates discrete Gaussian process to have a new, continuous representation as a DiscreteLowRankGaussianProcess, using nearest neigbor interpolation (for both mean and covariance function)
Interpolates discrete Gaussian process to have a new, continuous representation as a DiscreteLowRankGaussianProcess, using nearest neigbor interpolation (for both mean and covariance function)
- Definition Classes
- DiscreteLowRankGaussianProcess → DiscreteGaussianProcess
- Annotations
- @deprecated
- Deprecated
(Since version 0.16) please use the interpolate method with a NearestNeighborInterpolator instead