diff --git a/GPy/core/priors.py b/GPy/core/priors.py
index b86024d0..7b6379de 100644
--- a/GPy/core/priors.py
+++ b/GPy/core/priors.py
@@ -136,6 +136,7 @@ def gamma_from_EV(E, V):
     warnings.warn("use Gamma.from_EV to create Gamma Prior", FutureWarning)
     return Gamma.from_EV(E, V)
 
+
 class Gamma(Prior):
     """
     Implementation of the Gamma probability function, coupled with random variables.
diff --git a/GPy/inference/SCG.py b/GPy/inference/SCG.py
index 1cec0baa..5753be7f 100644
--- a/GPy/inference/SCG.py
+++ b/GPy/inference/SCG.py
@@ -63,7 +63,7 @@ def SCG(f, gradf, x, optargs=(), maxiters=500, max_f_eval=500, display=True, xto
     success = True # Force calculation of directional derivs.
     nsuccess = 0 # nsuccess counts number of successes.
     beta = 1.0 # Initial scale parameter.
-    betamin = 1.0e-15 # Lower bound on scale.
+    betamin = 1.0e-60 # Lower bound on scale.
     betamax = 1.0e100 # Upper bound on scale.
     status = "Not converged"
 
diff --git a/GPy/inference/SGD.py b/GPy/inference/SGD.py
index 7cb7566f..7543a819 100644
--- a/GPy/inference/SGD.py
+++ b/GPy/inference/SGD.py
@@ -192,7 +192,7 @@ class opt_SGD(Optimizer):
         if self.model.N == 0 or Y.std() == 0.0:
             return 0, step, self.model.N
 
-        self.model.likelihood._bias = Y.mean()
+        self.model.likelihood._offset = Y.mean()
         self.model.likelihood._scale = Y.std()
         self.model.likelihood.set_data(Y)
         # self.model.likelihood.V = self.model.likelihood.Y*self.model.likelihood.precision
@@ -219,9 +219,9 @@ class opt_SGD(Optimizer):
         self.restore_constraints(ci)
 
         self.model.grads[j] = fp
-        # restore likelihood _bias and _scale, otherwise when we call set_data(y) on
+        # restore likelihood _offset and _scale, otherwise when we call set_data(y) on
         # the next feature, it will get normalized with the mean and std of this one.
-        self.model.likelihood._bias = 0
+        self.model.likelihood._offset = 0
         self.model.likelihood._scale = 1
 
         return f, step, self.model.N
@@ -266,7 +266,7 @@ class opt_SGD(Optimizer):
 
         self.model.likelihood.YYT = 0
         self.model.likelihood.trYYT = 0
-        self.model.likelihood._bias = 0.0
+        self.model.likelihood._offset = 0.0
         self.model.likelihood._scale = 1.0
 
         N, Q = self.model.X.shape
diff --git a/GPy/likelihoods/Gaussian.py b/GPy/likelihoods/Gaussian.py
index d87b1b98..6c3c4edf 100644
--- a/GPy/likelihoods/Gaussian.py
+++ b/GPy/likelihoods/Gaussian.py
@@ -19,12 +19,12 @@ class Gaussian(likelihood):
 
         # normalization
         if normalize:
-            self._bias = data.mean(0)[None, :]
+            self._offset = data.mean(0)[None, :]
             self._scale = data.std(0)[None, :]
             # Don't scale outputs which have zero variance to zero.
             self._scale[np.nonzero(self._scale == 0.)] = 1.0e-3
         else:
-            self._bias = np.zeros((1, self.D))
+            self._offset = np.zeros((1, self.D))
             self._scale = np.ones((1, self.D))
 
         self.set_data(data)
@@ -36,7 +36,7 @@ class Gaussian(likelihood):
         self.data = data
         self.N, D = data.shape
         assert D == self.D
-        self.Y = (self.data - self._bias) / self._scale
+        self.Y = (self.data - self._offset) / self._scale
         if D > self.N:
             self.YYT = np.dot(self.Y, self.Y.T)
             self.trYYT = np.trace(self.YYT)
@@ -66,7 +66,7 @@ class Gaussian(likelihood):
         """
         Un-normalize the prediction and add the likelihood variance, then return the 5%, 95% interval
         """
-        mean = mu * self._scale + self._bias
+        mean = mu * self._scale + self._offset
         if full_cov:
             if self.D > 1:
                 raise NotImplementedError, "TODO"
diff --git a/GPy/models/Bayesian_GPLVM.py b/GPy/models/Bayesian_GPLVM.py
index dcef5291..0b0797a5 100644
--- a/GPy/models/Bayesian_GPLVM.py
+++ b/GPy/models/Bayesian_GPLVM.py
@@ -218,20 +218,19 @@ class Bayesian_GPLVM(sparse_GP, GPLVM):
         return means, covars
 
 
-    def plot_X_1d(self, fig=None, axes=None, fig_num="LVM mu S 1d", colors=None):
+    def plot_X_1d(self, ax=None, fignum=None, colors=None):
         """
         Plot latent space X in 1D:
 
             -if fig is given, create Q subplots in fig and plot in these
-            -if axes is given plot Q 1D latent space plots of X into each `axis`
-            -if neither fig nor axes is given create a figure with fig_num and plot in there
+            -if ax is given plot Q 1D latent space plots of X into each `axis`
+            -if neither fig nor ax is given create a figure with fignum and plot in there
 
         colors:
             colors of different latent space dimensions Q
         """
         import pylab
-        if fig is None and axes is None:
-            fig = pylab.figure(num=fig_num, figsize=(8, min(12, (2 * self.X.shape[1]))))
+        fig = pylab.figure(num=fignum, figsize=(8, min(12, (2 * self.X.shape[1]))))
         if colors is None:
             colors = pylab.gca()._get_lines.color_cycle
             pylab.clf()
@@ -240,10 +239,10 @@ class Bayesian_GPLVM(sparse_GP, GPLVM):
         plots = []
         x = np.arange(self.X.shape[0])
         for i in range(self.X.shape[1]):
-            if axes is None:
+            if ax is None:
                 ax = fig.add_subplot(self.X.shape[1], 1, i + 1)
             else:
-                ax = axes[i]
+                ax = ax[i]
             ax.plot(self.X, c='k', alpha=.3)
             plots.extend(ax.plot(x, self.X.T[i], c=colors.next(), label=r"$\mathbf{{X_{{{}}}}}$".format(i)))
             ax.fill_between(x,