Common Parameter: casOptml
CASL Syntax
Parameter Descriptions
algorithm="HF" | "LBFGS" | "QUANEW" | "SGD"
lbfgsOpt={lbfgsOptions}
LBFGS solver option set.
To simplify, you can specify only a value for the numCorrections parameter. In this case, the other parameters in the list use default values.
| The lbfgsOptions value can be one or more of the following: |
lineSearchMethod="ARMIJO" | "HYBRID" | "MORETHUENTE" | "STRONGWOLFE" | "WOLFE"
Specifies Line-search algorithms used in LBFGS solver.
| Default | MORETHUENTE |
numCorrections=64-bit-integer
Specifies the number of corrections used in the LBFGS update.
| Default | 20 |
| Minimum value | 1 |
optmlOpt={optmlOptions}
Common option set.
To simplify, you can specify only a value for the regL1 parameter. In this case, the other parameters in the list use default values.
| The optmlOptions value can be one or more of the following: |
clipWeightMaxNorm=double
Specifies the value to rescale the weights when the L2-norm of the weights exceeds the value.
| Default | 0 |
| Minimum value | 0 |
fConv=double
Specifies a stopping value when the objective fails to change more than that value in at least fConvWindow iterations for LBFGS solver.
| Default | 1e-05 |
| Minimum value | 0 |
fConvWindow=64-bit-integer
Specifies an iteration window for application of fConv convergence criteria used by LBFGS solver.
| Default | 1 |
| Minimum value | 1 |
gTol=double
Specifies the stopping tolerance for the first-order optimality error.
| Default | 1e-05 |
| Minimum value | 0 |
maxEvals=64-bit-integer
Specifies the maximum number of function evaluations allowed for optimization.
| Default | 0 |
| Minimum value | 0 |
maxIters=64-bit-integer
Specifies the maximum iterations allowed for optimization.
| Default | 10 |
| Minimum value | 0 |
maxTime=double
Specifies the maximum time (in seconds) allowed for optimization,
| Default | 0 |
| Minimum value | 0 |
regL1=double
Specifies the L1 regularization parameter, the value must be nonnegative.
| Default | 0 |
| Minimum value | 0 |
regL2=double
Specifies the L2 regularization parameter, the value must be nonnegative.
| Default | 0 |
| Minimum value | 0 |
printOpt={optmlPrintOptions}
Print log and display output option set.
To simplify, you can specify only a value for the printLevel parameter. In this case, the other parameters in the list use default values.
| The optmlPrintOptions value can be one or more of the following: |
logLevel=64-bit-integer
Specifies output display level.
| Default | 0 |
| Minimum value | 0 |
printFreq=64-bit-integer
Specifies the frequency the iteration log is printed.
| Default | 1 |
| Minimum value | 1 |
sgdOpt={sgdOptions}
SGD solver option set.
To simplify, you can specify only a value for the learningRate parameter. In this case, the other parameters in the list use default values.
| The sgdOptions value can be one or more of the following: |
adaptiveRate=TRUE | FALSE
Specifies the adaptive rate parameter for SGD,
| Default | FALSE |
annealingRate=double
Specifies the annealing parameter.
| Default | 1e-06 |
| Minimum value | 0 |
commFreq=64-bit-integer
Specifies the number of minibatches that each computational thread processes before weights are synchronized across all threads and nodes.
| Minimum value | 0 |
learningRate=double
Specifies the learning rate parameter for SGD.
| Default | 0.001 |
| Minimum value | 0 |
miniBatchSize=64-bit-integer
Specifies the size of the minibatches used in SGD.
| Default | 1 |
| Minimum value | 1 |
momentum=double
Specifies the value for momentum for SGD.
| Default | 0 |
| Range | 0–1 |
seed=64-bit-integer
Specifies the seed for random access of observations on each thread for the SGD algorithm.
useLocking=TRUE | FALSE
If true, thread aggregation is performed using locks, otherwise, atomic (non-deterministic) operation.
| Default | FALSE |
state={optmlState}
Save state option set.
To simplify, you can specify only a value for the table parameter. In this case, the other parameters in the list use default values.
| The optmlState value can be one or more of the following: |
checkpointFreq=64-bit-integer
Specifies the frequency of saving iteration state.
| Default | 0 |
| Minimum value | 0 |
saveBest=TRUE | FALSE
Specifies whether to save best solutions.
| Default | TRUE |
table={casouttable}
Specifies save state table name.
To simplify, you can specify only a value for the name parameter. In this case, the other parameters in the list use default values.
caslib="string"
specifies the name of the caslib to use.
compress=TRUE | FALSE
when set to True, data compression is applied to the table.
| Default | FALSE |
label="string"
specifies the descriptive label to associate with the table.
maxMemSize=64-bit-integer
specifies the maximum amount of physical memory, in bytes, to allocate for the table. After this threshold is reached, the server uses temporary files and operating system facilities for memory management.
| TIP | You can enclose the value in quotation marks and specify B, K, M, G, or T as a suffix to indicate the units. For example, "8M" specifies eight megabytes. |
name="table-name"
specifies the name to associate with the table.
onDemand=TRUE | FALSE
when set to True, table access is less aggressive with virtual memory use.
| Default | TRUE |
promote=TRUE | FALSE
when set to True, the output table is added with a global scope. This enables other sessions to access the table, subject to access controls. The target caslib must also have a global scope.
| Default | FALSE |
replace=TRUE | FALSE
specifies whether to overwrite an existing table with the same name.
| Default | FALSE |
replication=integer
specifies the number of copies of the table to make for fault tolerance. Larger values result in slower performance and use more memory, but provide high availability for data in the event of a node failure.
| Default | 1 |
| Minimum value | 0 |
timeStamp="string"
specifies the timestamp to apply to the table. Specify the value in the form that is appropriate for your session locale.
validate={optmlValidate}
Validation option set.
To simplify, you can specify only a value for the frequency parameter. In this case, the other parameters in the list use default values.
| The optmlValidate value can be one or more of the following: |
frequency=64-bit-integer
Specifies how frequently (in epochs) that validation occurs.
| Default | 0 |
| Minimum value | 0 |
goal=double
Specifies a goal for the validation misclassification rate. When misclassification gets below this goal, the optimization will stop.
| Default | 0 |
stagnation=64-bit-integer
Specifies a number of consecutive validations with increasing misclassification rates that are allowed before early termination of the optimization.
| Default | 0 |
| Minimum value | 0 |
Lua Syntax
Parameter Descriptions
algorithm="HF" | "LBFGS" | "QUANEW" | "SGD"
lbfgsOpt={lbfgsOptions}
LBFGS solver option set.
To simplify, you can specify only a value for the numCorrections parameter. In this case, the other parameters in the list use default values.
| The lbfgsOptions value can be one or more of the following: |
lineSearchMethod="ARMIJO" | "HYBRID" | "MORETHUENTE" | "STRONGWOLFE" | "WOLFE"
Specifies Line-search algorithms used in LBFGS solver.
| Default | MORETHUENTE |
numCorrections=64-bit-integer
Specifies the number of corrections used in the LBFGS update.
| Default | 20 |
| Minimum value | 1 |
optmlOpt={optmlOptions}
Common option set.
To simplify, you can specify only a value for the regL1 parameter. In this case, the other parameters in the list use default values.
| The optmlOptions value can be one or more of the following: |
clipWeightMaxNorm=double
Specifies the value to rescale the weights when the L2-norm of the weights exceeds the value.
| Default | 0 |
| Minimum value | 0 |
fConv=double
Specifies a stopping value when the objective fails to change more than that value in at least fConvWindow iterations for LBFGS solver.
| Default | 1e-05 |
| Minimum value | 0 |
fConvWindow=64-bit-integer
Specifies an iteration window for application of fConv convergence criteria used by LBFGS solver.
| Default | 1 |
| Minimum value | 1 |
gTol=double
Specifies the stopping tolerance for the first-order optimality error.
| Default | 1e-05 |
| Minimum value | 0 |
maxEvals=64-bit-integer
Specifies the maximum number of function evaluations allowed for optimization.
| Default | 0 |
| Minimum value | 0 |
maxIters=64-bit-integer
Specifies the maximum iterations allowed for optimization.
| Default | 10 |
| Minimum value | 0 |
maxTime=double
Specifies the maximum time (in seconds) allowed for optimization,
| Default | 0 |
| Minimum value | 0 |
regL1=double
Specifies the L1 regularization parameter, the value must be nonnegative.
| Default | 0 |
| Minimum value | 0 |
regL2=double
Specifies the L2 regularization parameter, the value must be nonnegative.
| Default | 0 |
| Minimum value | 0 |
printOpt={optmlPrintOptions}
Print log and display output option set.
To simplify, you can specify only a value for the printLevel parameter. In this case, the other parameters in the list use default values.
| The optmlPrintOptions value can be one or more of the following: |
logLevel=64-bit-integer
Specifies output display level.
| Default | 0 |
| Minimum value | 0 |
printFreq=64-bit-integer
Specifies the frequency the iteration log is printed.
| Default | 1 |
| Minimum value | 1 |
sgdOpt={sgdOptions}
SGD solver option set.
To simplify, you can specify only a value for the learningRate parameter. In this case, the other parameters in the list use default values.
| The sgdOptions value can be one or more of the following: |
adaptiveRate=true | false
Specifies the adaptive rate parameter for SGD,
| Default | false |
annealingRate=double
Specifies the annealing parameter.
| Default | 1e-06 |
| Minimum value | 0 |
commFreq=64-bit-integer
Specifies the number of minibatches that each computational thread processes before weights are synchronized across all threads and nodes.
| Minimum value | 0 |
learningRate=double
Specifies the learning rate parameter for SGD.
| Default | 0.001 |
| Minimum value | 0 |
miniBatchSize=64-bit-integer
Specifies the size of the minibatches used in SGD.
| Default | 1 |
| Minimum value | 1 |
momentum=double
Specifies the value for momentum for SGD.
| Default | 0 |
| Range | 0–1 |
seed=64-bit-integer
Specifies the seed for random access of observations on each thread for the SGD algorithm.
useLocking=true | false
If true, thread aggregation is performed using locks, otherwise, atomic (non-deterministic) operation.
| Default | false |
state={optmlState}
Save state option set.
To simplify, you can specify only a value for the table parameter. In this case, the other parameters in the list use default values.
| The optmlState value can be one or more of the following: |
checkpointFreq=64-bit-integer
Specifies the frequency of saving iteration state.
| Default | 0 |
| Minimum value | 0 |
saveBest=true | false
Specifies whether to save best solutions.
| Default | true |
table={casouttable}
Specifies save state table name.
To simplify, you can specify only a value for the name parameter. In this case, the other parameters in the list use default values.
caslib="string"
specifies the name of the caslib to use.
compress=true | false
when set to True, data compression is applied to the table.
| Default | false |
label="string"
specifies the descriptive label to associate with the table.
maxMemSize=64-bit-integer
specifies the maximum amount of physical memory, in bytes, to allocate for the table. After this threshold is reached, the server uses temporary files and operating system facilities for memory management.
| TIP | You can enclose the value in quotation marks and specify B, K, M, G, or T as a suffix to indicate the units. For example, "8M" specifies eight megabytes. |
name="table-name"
specifies the name to associate with the table.
onDemand=true | false
when set to True, table access is less aggressive with virtual memory use.
| Default | true |
promote=true | false
when set to True, the output table is added with a global scope. This enables other sessions to access the table, subject to access controls. The target caslib must also have a global scope.
| Default | false |
replace=true | false
specifies whether to overwrite an existing table with the same name.
| Default | false |
replication=integer
specifies the number of copies of the table to make for fault tolerance. Larger values result in slower performance and use more memory, but provide high availability for data in the event of a node failure.
| Default | 1 |
| Minimum value | 0 |
timeStamp="string"
specifies the timestamp to apply to the table. Specify the value in the form that is appropriate for your session locale.
validate={optmlValidate}
Validation option set.
To simplify, you can specify only a value for the frequency parameter. In this case, the other parameters in the list use default values.
| The optmlValidate value can be one or more of the following: |
frequency=64-bit-integer
Specifies how frequently (in epochs) that validation occurs.
| Default | 0 |
| Minimum value | 0 |
goal=double
Specifies a goal for the validation misclassification rate. When misclassification gets below this goal, the optimization will stop.
| Default | 0 |
stagnation=64-bit-integer
Specifies a number of consecutive validations with increasing misclassification rates that are allowed before early termination of the optimization.
| Default | 0 |
| Minimum value | 0 |
Python Syntax
Parameter Descriptions
"algorithm":"HF" | "LBFGS" | "QUANEW" | "SGD"
"lbfgsOpt"={lbfgsOptions}
LBFGS solver option set.
To simplify, you can specify only a value for the numCorrections parameter. In this case, the other parameters in the list use default values.
| The lbfgsOptions value can be one or more of the following: |
"lineSearchMethod":"ARMIJO" | "HYBRID" | "MORETHUENTE" | "STRONGWOLFE" | "WOLFE"
Specifies Line-search algorithms used in LBFGS solver.
| Default | MORETHUENTE |
"numCorrections":64-bit-integer
Specifies the number of corrections used in the LBFGS update.
| Default | 20 |
| Minimum value | 1 |
"optmlOpt"={optmlOptions}
Common option set.
To simplify, you can specify only a value for the regL1 parameter. In this case, the other parameters in the list use default values.
| The optmlOptions value can be one or more of the following: |
"clipWeightMaxNorm":double
Specifies the value to rescale the weights when the L2-norm of the weights exceeds the value.
| Default | 0 |
| Minimum value | 0 |
"fConv":double
Specifies a stopping value when the objective fails to change more than that value in at least fConvWindow iterations for LBFGS solver.
| Default | 1e-05 |
| Minimum value | 0 |
"fConvWindow":64-bit-integer
Specifies an iteration window for application of fConv convergence criteria used by LBFGS solver.
| Default | 1 |
| Minimum value | 1 |
"gTol":double
Specifies the stopping tolerance for the first-order optimality error.
| Default | 1e-05 |
| Minimum value | 0 |
"maxEvals":64-bit-integer
Specifies the maximum number of function evaluations allowed for optimization.
| Default | 0 |
| Minimum value | 0 |
"maxIters":64-bit-integer
Specifies the maximum iterations allowed for optimization.
| Default | 10 |
| Minimum value | 0 |
"maxTime":double
Specifies the maximum time (in seconds) allowed for optimization,
| Default | 0 |
| Minimum value | 0 |
"regL1":double
Specifies the L1 regularization parameter, the value must be nonnegative.
| Default | 0 |
| Minimum value | 0 |
"regL2":double
Specifies the L2 regularization parameter, the value must be nonnegative.
| Default | 0 |
| Minimum value | 0 |
"printOpt"={optmlPrintOptions}
Print log and display output option set.
To simplify, you can specify only a value for the printLevel parameter. In this case, the other parameters in the list use default values.
| The optmlPrintOptions value can be one or more of the following: |
"logLevel":64-bit-integer
Specifies output display level.
| Default | 0 |
| Minimum value | 0 |
"printFreq":64-bit-integer
Specifies the frequency the iteration log is printed.
| Default | 1 |
| Minimum value | 1 |
"sgdOpt"={sgdOptions}
SGD solver option set.
To simplify, you can specify only a value for the learningRate parameter. In this case, the other parameters in the list use default values.
| The sgdOptions value can be one or more of the following: |
"adaptiveRate":True | False
Specifies the adaptive rate parameter for SGD,
| Default | False |
"annealingRate":double
Specifies the annealing parameter.
| Default | 1e-06 |
| Minimum value | 0 |
"commFreq":64-bit-integer
Specifies the number of minibatches that each computational thread processes before weights are synchronized across all threads and nodes.
| Minimum value | 0 |
"learningRate":double
Specifies the learning rate parameter for SGD.
| Default | 0.001 |
| Minimum value | 0 |
"miniBatchSize":64-bit-integer
Specifies the size of the minibatches used in SGD.
| Default | 1 |
| Minimum value | 1 |
"momentum":double
Specifies the value for momentum for SGD.
| Default | 0 |
| Range | 0–1 |
"seed":64-bit-integer
Specifies the seed for random access of observations on each thread for the SGD algorithm.
"useLocking":True | False
If true, thread aggregation is performed using locks, otherwise, atomic (non-deterministic) operation.
| Default | False |
"state"={optmlState}
Save state option set.
To simplify, you can specify only a value for the table parameter. In this case, the other parameters in the list use default values.
| The optmlState value can be one or more of the following: |
"checkpointFreq":64-bit-integer
Specifies the frequency of saving iteration state.
| Default | 0 |
| Minimum value | 0 |
"saveBest":True | False
Specifies whether to save best solutions.
| Default | True |
"table"={casouttable}
Specifies save state table name.
To simplify, you can specify only a value for the name parameter. In this case, the other parameters in the list use default values.
"caslib":"string"
specifies the name of the caslib to use.
"compress":True | False
when set to True, data compression is applied to the table.
| Default | False |
"label":"string"
specifies the descriptive label to associate with the table.
"maxMemSize":64-bit-integer
specifies the maximum amount of physical memory, in bytes, to allocate for the table. After this threshold is reached, the server uses temporary files and operating system facilities for memory management.
| TIP | You can enclose the value in quotation marks and specify B, K, M, G, or T as a suffix to indicate the units. For example, "8M" specifies eight megabytes. |
"name":"table-name"
specifies the name to associate with the table.
"onDemand":True | False
when set to True, table access is less aggressive with virtual memory use.
| Default | True |
"promote":True | False
when set to True, the output table is added with a global scope. This enables other sessions to access the table, subject to access controls. The target caslib must also have a global scope.
| Default | False |
"replace":True | False
specifies whether to overwrite an existing table with the same name.
| Default | False |
"replication":integer
specifies the number of copies of the table to make for fault tolerance. Larger values result in slower performance and use more memory, but provide high availability for data in the event of a node failure.
| Default | 1 |
| Minimum value | 0 |
"timeStamp":"string"
specifies the timestamp to apply to the table. Specify the value in the form that is appropriate for your session locale.
"validate"={optmlValidate}
Validation option set.
To simplify, you can specify only a value for the frequency parameter. In this case, the other parameters in the list use default values.
| The optmlValidate value can be one or more of the following: |
"frequency":64-bit-integer
Specifies how frequently (in epochs) that validation occurs.
| Default | 0 |
| Minimum value | 0 |
"goal":double
Specifies a goal for the validation misclassification rate. When misclassification gets below this goal, the optimization will stop.
| Default | 0 |
"stagnation":64-bit-integer
Specifies a number of consecutive validations with increasing misclassification rates that are allowed before early termination of the optimization.
| Default | 0 |
| Minimum value | 0 |