diff --git a/src/Microsoft.ML.StandardTrainers/Standard/Online/AveragedLinear.cs b/src/Microsoft.ML.StandardTrainers/Standard/Online/AveragedLinear.cs
index 0bcd1b3c6e..8d8ef61f97 100644
--- a/src/Microsoft.ML.StandardTrainers/Standard/Online/AveragedLinear.cs
+++ b/src/Microsoft.ML.StandardTrainers/Standard/Online/AveragedLinear.cs
@@ -21,7 +21,7 @@ namespace Microsoft.ML.Trainers
public abstract class AveragedLinearOptions : OnlineLinearOptions
{
///
- /// Learning rate.
+ /// Learning rate.
///
[Argument(ArgumentType.AtMostOnce, HelpText = "Learning rate", ShortName = "lr", SortOrder = 50)]
[TGUI(Label = "Learning rate", SuggestedSweeps = "0.01,0.1,0.5,1.0")]
@@ -61,7 +61,7 @@ public abstract class AveragedLinearOptions : OnlineLinearOptions
public bool LazyUpdate = true;
///
- /// The L2 weight for regularization.
+ /// The L2 weight for regularization.
///
[Argument(ArgumentType.AtMostOnce, HelpText = "L2 Regularization Weight", ShortName = "reg,L2RegularizerWeight", SortOrder = 50)]
[TGUI(Label = "L2 Regularization Weight")]
diff --git a/src/Microsoft.ML.StandardTrainers/Standard/Online/AveragedPerceptron.cs b/src/Microsoft.ML.StandardTrainers/Standard/Online/AveragedPerceptron.cs
index 50a4b1c61c..97f66ecdf8 100644
--- a/src/Microsoft.ML.StandardTrainers/Standard/Online/AveragedPerceptron.cs
+++ b/src/Microsoft.ML.StandardTrainers/Standard/Online/AveragedPerceptron.cs
@@ -79,18 +79,18 @@ public sealed class AveragedPerceptronTrainer : AveragedLinearTrainer
- /// A custom loss.
+ /// A custom loss.
///
[Argument(ArgumentType.Multiple, Name = "LossFunction", HelpText = "Loss Function", ShortName = "loss", SortOrder = 50)]
internal ISupportClassificationLossFactory ClassificationLossFunctionFactory = new HingeLoss.Options();
///
- /// A custom loss.
+ /// A custom loss.
///
public IClassificationLoss LossFunction { get; set; }
///
- /// The calibrator for producing probabilities. Default is exponential (aka Platt) calibration.
+ /// The calibrator for producing probabilities. Default is exponential (aka Platt) calibration.
///
[Argument(ArgumentType.AtMostOnce, HelpText = "The calibrator kind to apply to the predictor. Specify null for no calibration", Visibility = ArgumentAttribute.VisibilityType.EntryPointsOnly)]
internal ICalibratorTrainerFactory Calibrator = new PlattCalibratorTrainerFactory();
diff --git a/src/Microsoft.ML.StandardTrainers/Standard/Online/OnlineGradientDescent.cs b/src/Microsoft.ML.StandardTrainers/Standard/Online/OnlineGradientDescent.cs
index a0f678ae95..53e6745243 100644
--- a/src/Microsoft.ML.StandardTrainers/Standard/Online/OnlineGradientDescent.cs
+++ b/src/Microsoft.ML.StandardTrainers/Standard/Online/OnlineGradientDescent.cs
@@ -52,7 +52,7 @@ public sealed class Options : AveragedLinearOptions
internal ISupportRegressionLossFactory RegressionLossFunctionFactory = new SquaredLossFactory();
///
- /// A custom loss.
+ /// A custom loss.
///
public IRegressionLoss LossFunction { get; set; }
diff --git a/src/Microsoft.ML.StandardTrainers/Standard/SdcaBinary.cs b/src/Microsoft.ML.StandardTrainers/Standard/SdcaBinary.cs
index 5c763998c2..bbe982b6cb 100644
--- a/src/Microsoft.ML.StandardTrainers/Standard/SdcaBinary.cs
+++ b/src/Microsoft.ML.StandardTrainers/Standard/SdcaBinary.cs
@@ -157,7 +157,7 @@ public abstract class SdcaTrainerBase : Stochast
public abstract class OptionsBase : TrainerInputBaseWithWeight
{
///
- /// The L2 regularization hyperparameter.
+ /// The L2 regularization hyperparameter.
///
[Argument(ArgumentType.AtMostOnce, HelpText = "L2 regularizer constant. By default the l2 constant is automatically inferred based on data set.", NullName = "", ShortName = "l2, L2Const", SortOrder = 1)]
[TGUI(Label = "L2 Regularizer Constant", SuggestedSweeps = ",1e-7,1e-6,1e-5,1e-4,1e-3,1e-2")]
@@ -166,7 +166,7 @@ public abstract class OptionsBase : TrainerInputBaseWithWeight
// REVIEW: make the default positive when we know how to consume a sparse model
///
- /// The L1 regularization hyperparameter.
+ /// The L1 regularization hyperparameter.
///
[Argument(ArgumentType.AtMostOnce, HelpText = "L1 soft threshold (L1/L2). Note that it is easier to control and sweep using the threshold parameter than the raw L1-regularizer constant. By default the l1 threshold is automatically inferred based on data set.",
NullName = "", Name = "L1Threshold", ShortName = "l1", SortOrder = 2)]
@@ -1547,7 +1547,7 @@ private protected override BinaryPredictionTransformer MakeTra
///
/// The for training a binary logistic regression classification model using the stochastic dual coordinate ascent method.
- /// The trained model is calibrated and can produce probability by feeding the output value of the
+ /// The trained model is calibrated and can produce probability by feeding the output value of the
/// linear function to a .
///
///
@@ -1623,7 +1623,7 @@ public sealed class SdcaNonCalibratedBinaryTrainer : SdcaBinaryTrainerBase
- /// The custom loss.
+ /// The custom loss.
///
///
/// If unspecified, will be used.
@@ -1632,7 +1632,7 @@ public sealed class Options : BinaryOptionsBase
internal ISupportSdcaClassificationLossFactory LossFunctionFactory = new LogLossFactory();
///
- /// The custom loss.
+ /// The custom loss.
///
///
/// If unspecified, will be used.
@@ -1776,7 +1776,7 @@ public abstract class SgdBinaryTrainerBase :
public class OptionsBase : TrainerInputBaseWithWeight
{
///
- /// The L2 weight for regularization.
+ /// The L2 weight for regularization.
///
[Argument(ArgumentType.AtMostOnce, HelpText = "L2 Regularization constant", ShortName = "l2, L2Weight", SortOrder = 50)]
[TGUI(Label = "L2 Regularization Constant", SuggestedSweeps = "1e-7,5e-7,1e-6,5e-6,1e-5")]
@@ -1814,7 +1814,7 @@ public class OptionsBase : TrainerInputBaseWithWeight
public int NumberOfIterations = Defaults.NumberOfIterations;
///
- /// The initial learning rate used by SGD.
+ /// The initial learning rate used by SGD.
///
[Argument(ArgumentType.AtMostOnce, HelpText = "Initial learning rate (only used by SGD)", Name = "InitialLearningRate", ShortName = "ilr,lr,InitLearningRate")]
[TGUI(Label = "Initial Learning Rate (for SGD)")]
@@ -2171,7 +2171,7 @@ private protected override void CheckLabel(RoleMappedData examples, out int weig
///
/// The for training logistic regression using a parallel stochastic gradient method.
- /// The trained model is calibrated and can produce probability by feeding the output value of the
+ /// The trained model is calibrated and can produce probability by feeding the output value of the
/// linear function to a .
///
///
diff --git a/src/Microsoft.ML.StandardTrainers/Standard/SdcaMulticlass.cs b/src/Microsoft.ML.StandardTrainers/Standard/SdcaMulticlass.cs
index 2344651d59..bc4a578c3a 100644
--- a/src/Microsoft.ML.StandardTrainers/Standard/SdcaMulticlass.cs
+++ b/src/Microsoft.ML.StandardTrainers/Standard/SdcaMulticlass.cs
@@ -42,7 +42,7 @@ public abstract class SdcaMulticlassTrainerBase : SdcaTrainerBase
- /// The custom loss.
+ /// The custom loss.
///
///
/// If unspecified, will be used.
diff --git a/src/Microsoft.ML.StandardTrainers/Standard/SdcaRegression.cs b/src/Microsoft.ML.StandardTrainers/Standard/SdcaRegression.cs
index 3b242f907c..1f27c19bcc 100644
--- a/src/Microsoft.ML.StandardTrainers/Standard/SdcaRegression.cs
+++ b/src/Microsoft.ML.StandardTrainers/Standard/SdcaRegression.cs
@@ -38,7 +38,7 @@ public sealed class SdcaRegressionTrainer : SdcaTrainerBase
- /// A custom loss.
+ /// A custom loss.
///
///
/// Defaults to
@@ -47,7 +47,7 @@ public sealed class Options : OptionsBase
internal ISupportSdcaRegressionLossFactory LossFunctionFactory = new SquaredLossFactory();
///
- /// A custom loss.
+ /// A custom loss.
///
///
/// Defaults to
diff --git a/src/Microsoft.ML.StandardTrainers/StandardTrainersCatalog.cs b/src/Microsoft.ML.StandardTrainers/StandardTrainersCatalog.cs
index 4eaeb9dc53..fd06f33389 100644
--- a/src/Microsoft.ML.StandardTrainers/StandardTrainersCatalog.cs
+++ b/src/Microsoft.ML.StandardTrainers/StandardTrainersCatalog.cs
@@ -25,8 +25,8 @@ public static class StandardTrainersCatalog
/// The features, or independent variables.
/// The name of the example weight column (optional).
/// The maximum number of passes through the training dataset; set to 1 to simulate online learning.
- /// The initial learning rate used by SGD.
- /// The L2 weight for regularization.
+ /// The initial learning rate used by SGD.
+ /// The L2 weight for regularization.
///
///
/// The name of the label column, or dependent variable.
/// The features, or independent variables.
/// The name of the example weight column (optional).
- /// The loss function minimized in the training process. Using, for example, leads to a support vector machine trainer.
+ /// The loss function minimized in the training process. Using, for example, leads to a support vector machine trainer.
/// The maximum number of passes through the training dataset; set to 1 to simulate online learning.
- /// The initial learning rate used by SGD.
- /// The L2 weight for regularization.
+ /// The initial learning rate used by SGD.
+ /// The L2 weight for regularization.
///
///
/// The name of the label column.
/// The name of the feature column.
/// The name of the example weight column (optional).
- /// The loss function minimized in the training process. Using, for example, its default leads to a least square trainer.
- /// The L2 weight for regularization.
- /// The L1 regularization hyperparameter. Higher values will tend to lead to more sparse model.
+ /// The loss function minimized in the training process. Using, for example, its default leads to a least square trainer.
+ /// The L2 weight for regularization.
+ /// The L1 regularization hyperparameter. Higher values will tend to lead to more sparse model.
/// The maximum number of passes to perform over the data.
///
///
@@ -187,8 +187,8 @@ public static SdcaRegressionTrainer Sdca(this RegressionCatalog.RegressionTraine
/// The name of the label column.
/// The name of the feature column.
/// The name of the example weight column (optional).
- /// The L2 weight for regularization.
- /// The L1 regularization hyperparameter. Higher values will tend to lead to more sparse model.
+ /// The L2 weight for regularization.
+ /// The L1 regularization hyperparameter. Higher values will tend to lead to more sparse model.
/// The maximum number of passes to perform over the data.
///
///
@@ -239,9 +239,9 @@ public static SdcaLogisticRegressionBinaryTrainer SdcaLogisticRegression(
/// The name of the label column.
/// The name of the feature column.
/// The name of the example weight column (optional).
- /// The loss function minimized in the training process. Defaults to if not specified.
- /// The L2 weight for regularization.
- /// The L1 regularization hyperparameter. Higher values will tend to lead to more sparse model.
+ /// The loss function minimized in the training process. Defaults to if not specified.
+ /// The L2 weight for regularization.
+ /// The L1 regularization hyperparameter. Higher values will tend to lead to more sparse model.
/// The maximum number of passes to perform over the data.
///
///
@@ -287,8 +287,8 @@ public static SdcaNonCalibratedBinaryTrainer SdcaNonCalibrated(
/// The name of the label column.
/// The name of the feature column.
/// The name of the example weight column (optional).
- /// The L2 weight for regularization.
- /// The L1 regularization hyperparameter. Higher values will tend to lead to more sparse model.
+ /// The L2 weight for regularization.
+ /// The L1 regularization hyperparameter. Higher values will tend to lead to more sparse model.
/// The maximum number of passes to perform over the data.
///
///
@@ -337,9 +337,9 @@ public static SdcaMaximumEntropyMulticlassTrainer SdcaMaximumEntropy(this Multic
/// The name of the label column.
/// The name of the feature column.
/// The name of the example weight column (optional).
- /// The loss function to be minimized. Defaults to if not specified.
- /// The L2 weight for regularization.
- /// The L1 regularization hyperparameter. Higher values will tend to lead to more sparse model.
+ /// The loss function to be minimized. Defaults to if not specified.
+ /// The L2 weight for regularization.
+ /// The L1 regularization hyperparameter. Higher values will tend to lead to more sparse model.
/// The maximum number of passes to perform over the data.
///
///
@@ -388,13 +388,13 @@ public static SdcaNonCalibratedMulticlassTrainer SdcaNonCalibrated(this Multicla
/// The binary classification catalog trainer object.
/// The name of the label column. The column data must be .
/// The name of the feature column. The column data must be a known-sized vector of .
- /// The loss function minimized in the training process. If , would be used and lead to a max-margin averaged perceptron trainer.
- /// The initial learning rate used by SGD.
+ /// The loss function minimized in the training process. If , would be used and lead to a max-margin averaged perceptron trainer.
+ /// The initial learning rate used by SGD.
///
/// to decrease the as iterations progress; otherwise, .
/// Default is .
///
- /// The L2 weight for regularization.
+ /// The L2 weight for regularization.
/// Number of passes through the training dataset.
///
///
@@ -462,10 +462,10 @@ public IClassificationLoss CreateComponent(IHostEnvironment env)
/// The regression catalog trainer object.
/// The name of the label column.
/// The name of the feature column.
- /// The loss function minimized in the training process. Using, for example, leads to a least square trainer.
- /// The initial learning rate used by SGD.
+ /// The loss function minimized in the training process. Using, for example, leads to a least square trainer.
+ /// The initial learning rate used by SGD.
/// Decrease learning rate as iterations progress.
- /// The L2 weight for regularization.
+ /// The L2 weight for regularization.
/// The number of passes through the training dataset.
public static OnlineGradientDescentTrainer OnlineGradientDescent(this RegressionCatalog.RegressionTrainers catalog,
string labelColumnName = DefaultColumnNames.Label,
@@ -505,8 +505,8 @@ public static OnlineGradientDescentTrainer OnlineGradientDescent(this Regression
/// The name of the feature column.
/// The name of the example weight column (optional).
/// Enforce non-negative weights.
- /// The L1 regularization hyperparameter. Higher values will tend to lead to more sparse model.
- /// The L2 weight for regularization.
+ /// The L1 regularization hyperparameter. Higher values will tend to lead to more sparse model.
+ /// The L2 weight for regularization.
/// Memory size for . Low=faster, less accurate.
/// Threshold for optimizer convergence.
///
@@ -559,8 +559,8 @@ public static LbfgsLogisticRegressionBinaryTrainer LbfgsLogisticRegression(this
/// The name of the label column.
/// The name of the feature column.
/// The name of the example weight column (optional).
- /// The L1 regularization hyperparameter. Higher values will tend to lead to more sparse model.
- /// The L2 weight for regularization.
+ /// The L1 regularization hyperparameter. Higher values will tend to lead to more sparse model.
+ /// The L2 weight for regularization.
/// Threshold for optimizer convergence.
/// Number of previous iterations to remember for estimating the Hessian. Lower values mean faster but less accurate estimates.
/// Enforce non-negative weights.
@@ -613,8 +613,8 @@ public static LbfgsPoissonRegressionTrainer LbfgsPoissonRegression(this Regressi
/// The name of the feature column.
/// The name of the example weight column (optional).
/// Enforce non-negative weights.
- /// The L1 regularization hyperparameter. Higher values will tend to lead to more sparse model.
- /// The L2 weight for regularization.
+ /// The L1 regularization hyperparameter. Higher values will tend to lead to more sparse model.
+ /// The L2 weight for regularization.
/// Memory size for . Low=faster, less accurate.
/// Threshold for optimizer convergence.
public static LbfgsMaximumEntropyMulticlassTrainer LbfgsMaximumEntropy(this MulticlassClassificationCatalog.MulticlassClassificationTrainers catalog,
diff --git a/src/Microsoft.ML.StaticPipe/SgdStatic.cs b/src/Microsoft.ML.StaticPipe/SgdStatic.cs
index e228a064ef..c0c02cb7e9 100644
--- a/src/Microsoft.ML.StaticPipe/SgdStatic.cs
+++ b/src/Microsoft.ML.StaticPipe/SgdStatic.cs
@@ -21,8 +21,8 @@ public static class SgdStaticExtensions
/// The name of the feature column.
/// The name for the example weight column.
/// The maximum number of iterations; set to 1 to simulate online learning.
- /// The initial learning rate used by SGD.
- /// The L2 weight for regularization.
+ /// The initial learning rate used by SGD.
+ /// The L2 weight for regularization.
/// A delegate that is called every time the
/// method is called on the
/// instance created out of this. This delegate will receive
@@ -101,8 +101,8 @@ public static (Scalar score, Scalar probability, Scalar pred
/// The name of the feature column.
/// The name for the example weight column.
/// The maximum number of iterations; set to 1 to simulate online learning.
- /// The initial learning rate used by SGD.
- /// The L2 weight for regularization.
+ /// The initial learning rate used by SGD.
+ /// The L2 weight for regularization.
/// The loss function to use.
/// A delegate that is called every time the
/// method is called on the