Refactor links to Hoffman paper

and use latex symbols for original parameter names

Author: jonaschn

gensim/models/atmodel.py

@@ -23,6 +23,9 @@
 <https://arxiv.org/abs/1207.4169>`_. The model correlates the authorship information with the topics to give a better
 insight on the subject knowledge of an author.
 
+.. _'Online Learning for LDA' by Hoffman et al.: online-lda_
+.. _online-lda: https://papers.neurips.cc/paper/2010/file/71f6278d140af599e06ad9bf1ba03cb0-Paper.pdf
+
 Example
 -------
 .. sourcecode:: pycon
@@ -185,9 +188,12 @@ def __init__(self, corpus=None, num_topics=100, id2word=None, author2doc=None, d
         iterations : int, optional
             Maximum number of times the model loops over each document.
         decay : float, optional
-            Controls how old documents are forgotten.
+            A number between (0.5, 1] to weight what percentage of the previous lambda value is forgotten
+            when each new document is examined. Corresponds to :math:`\\kappa` from
+            `'Online Learning for LDA' by Hoffman et al.`_
         offset : float, optional
-            Controls down-weighting of iterations.
+            Hyper-parameter that controls how much we will slow down the first steps the first few iterations.
+            Corresponds to :math:`\\tau_0` from `'Online Learning for LDA' by Hoffman et al.`_
         alpha : {float, numpy.ndarray of float, list of float, str}, optional
             A-priori belief on document-topic distribution, this can be:
                 * scalar for a symmetric prior over document-topic distribution,
@@ -618,15 +624,14 @@ def update(self, corpus=None, author2doc=None, doc2author=None, chunksize=None,
 
         Notes
         -----
-        This update also supports updating an already trained model (self)
-        with new documents from `corpus`: the two models are then merged in proportion to the number of old vs. new
-        documents. This feature is still experimental for non-stationary input streams.
+        This update also supports updating an already trained model (`self`) with new documents from `corpus`;
+        the two models are then merged in proportion to the number of old vs. new documents.
+        This feature is still experimental for non-stationary input streams.
 
-        For stationary input (no topic drift in new documents), on the other hand, this equals the online update of
-        `Hoffman et al. Stochastic Variational Inference
-        <http://www.jmlr.org/papers/volume14/hoffman13a/hoffman13a.pdf>`_ and is guaranteed to converge for any `decay`
-        in (0.5, 1.0>. Additionally, for smaller `corpus` sizes, an increasing `offset` may be beneficial (see
-        Table 1 in Hoffman et al.)
+        For stationary input (no topic drift in new documents), on the other hand, this equals the
+        online update of `'Online Learning for LDA' by Hoffman et al.`_
+        and is guaranteed to converge for any `decay` in (0.5, 1]. Additionally, for smaller corpus sizes, an
+        increasing `offset` may be beneficial (see Table 1 in the same paper).
 
         If update is called with authors that already exist in the model, it will resume training on not only new
         documents for that author, but also the previously seen documents. This is necessary for those authors' topic
@@ -653,9 +658,12 @@ def update(self, corpus=None, author2doc=None, doc2author=None, chunksize=None,
         chunksize : int, optional
             Controls the size of the mini-batches.
         decay : float, optional
-            Controls how old documents are forgotten.
+            A number between (0.5, 1] to weight what percentage of the previous lambda value is forgotten
+            when each new document is examined. Corresponds to :math:`\\kappa` from
+            `'Online Learning for LDA' by Hoffman et al.`_
         offset : float, optional
-            Controls down-weighting of iterations.
+            Hyper-parameter that controls how much we will slow down the first steps the first few iterations.
+            Corresponds to :math:`\\tau_0` from `'Online Learning for LDA' by Hoffman et al.`_
         passes : int, optional
             Number of times the model makes a pass over the entire training data.
         update_every : int, optional

gensim/models/ldamodel.py

@@ -14,9 +14,12 @@
 
 The core estimation code is based on the `onlineldavb.py script
 <https://github.com/blei-lab/onlineldavb/blob/master/onlineldavb.py>`_, by
-`Matthew D. Hoffman, David M. Blei, Francis Bach:
-Online Learning for Latent Dirichlet Allocation, NIPS 2010
-<https://papers.neurips.cc/paper/2010/file/71f6278d140af599e06ad9bf1ba03cb0-Paper.pdf>`_.
+Matthew D. Hoffman, David M. Blei, Francis Bach:
+`'Online Learning for Latent Dirichlet Allocation', NIPS 2010`_.
+
+.. _'Online Learning for Latent Dirichlet Allocation', NIPS 2010: online-lda_
+.. _'Online Learning for LDA' by Hoffman et al.: online-lda_
+.. _online-lda: https://papers.neurips.cc/paper/2010/file/71f6278d140af599e06ad9bf1ba03cb0-Paper.pdf
 
 The algorithm:
 
@@ -199,8 +202,7 @@ def blend(self, rhot, other, targetsize=None):
 
         The number of documents is stretched in both state objects, so that they are of comparable magnitude.
         This procedure corresponds to the stochastic gradient update from
-        `Hoffman et al. :"Online Learning for Latent Dirichlet Allocation"
-        <https://papers.neurips.cc/paper/2010/file/71f6278d140af599e06ad9bf1ba03cb0-Paper.pdf>`_, see equations (5) and (9).
+        `'Online Learning for LDA' by Hoffman et al.`_, see equations (5) and (9).
 
         Parameters
         ----------
@@ -312,9 +314,7 @@ def load(cls, fname, *args, **kwargs):
 
 
 class LdaModel(interfaces.TransformationABC, basemodel.BaseTopicModel):
-    """Train and use Online Latent Dirichlet Allocation models as presented in
-    `Hoffman et al. :"Online Learning for Latent Dirichlet Allocation"
-    <https://papers.neurips.cc/paper/2010/file/71f6278d140af599e06ad9bf1ba03cb0-Paper.pdf>`_.
+    """Train and use Online Latent Dirichlet Allocation models as presented in `'Online Learning for LDA' by Hoffman et al.`_
 
     Examples
     -------
@@ -396,13 +396,11 @@ def __init__(self, corpus=None, num_topics=100, id2word=None,
                 * 'auto': Learns an asymmetric prior from the corpus.
         decay : float, optional
             A number between (0.5, 1] to weight what percentage of the previous lambda value is forgotten
-            when each new document is examined. Corresponds to Kappa from
-            `Hoffman et al. :"Online Learning for Latent Dirichlet Allocation"
-            <https://papers.neurips.cc/paper/2010/file/71f6278d140af599e06ad9bf1ba03cb0-Paper.pdf>`_.
+            when each new document is examined.
+            Corresponds to :math:`\\kappa` from `'Online Learning for LDA' by Hoffman et al.`_
         offset : float, optional
             Hyper-parameter that controls how much we will slow down the first steps the first few iterations.
-            Corresponds to Tau_0 from `Hoffman et al. :"Online Learning for Latent Dirichlet Allocation"
-            <https://papers.neurips.cc/paper/2010/file/71f6278d140af599e06ad9bf1ba03cb0-Paper.pdf>`_.
+            Corresponds to :math:`\\tau_0` from `'Online Learning for LDA' by Hoffman et al.`_
         eval_every : int, optional
             Log perplexity is estimated every that many updates. Setting this to one slows down training by ~2x.
         iterations : int, optional
@@ -862,13 +860,15 @@ def update(self, corpus, chunksize=None, decay=None, offset=None,
 
         Notes
         -----
-        This update also supports updating an already trained model with new documents; the two models are then merged
-        in proportion to the number of old vs. new documents. This feature is still experimental for non-stationary
-        input streams. For stationary input (no topic drift in new documents), on the other hand, this equals the
-        online update of `Hoffman et al. :"Online Learning for Latent Dirichlet Allocation"
-        <https://papers.neurips.cc/paper/2010/file/71f6278d140af599e06ad9bf1ba03cb0-Paper.pdf>`_
-        and is guaranteed to converge for any `decay` in (0.5, 1.0). Additionally, for smaller corpus sizes, an
-        increasing `offset` may be beneficial (see Table 1 in the same paper).
+        This update also supports updating an already trained model (`self`) with new documents from `corpus`;
+        the two models are then merged in proportion to the number of old vs. new documents.
+        This feature is still experimental for non-stationary input streams.
+
+        For stationary input (no topic drift in new documents), on the other hand,
+        this equals the online update of `'Online Learning for LDA' by Hoffman et al.`_
+        and is guaranteed to converge for any `decay` in (0.5, 1].
+        Additionally, for smaller corpus sizes,
+        an increasing `offset` may be beneficial (see Table 1 in the same paper).
 
         Parameters
         ----------
@@ -879,13 +879,11 @@ def update(self, corpus, chunksize=None, decay=None, offset=None,
             Number of documents to be used in each training chunk.
         decay : float, optional
             A number between (0.5, 1] to weight what percentage of the previous lambda value is forgotten
-            when each new document is examined. Corresponds to Kappa from
-            `Hoffman et al. :"Online Learning for Latent Dirichlet Allocation"
-            <https://papers.neurips.cc/paper/2010/file/71f6278d140af599e06ad9bf1ba03cb0-Paper.pdf>`_.
+            when each new document is examined. Corresponds to :math:`\\kappa` from
+            `'Online Learning for LDA' by Hoffman et al.`_
         offset : float, optional
             Hyper-parameter that controls how much we will slow down the first steps the first few iterations.
-            Corresponds to Tau_0 from `Hoffman et al. :"Online Learning for Latent Dirichlet Allocation"
-            <https://papers.neurips.cc/paper/2010/file/71f6278d140af599e06ad9bf1ba03cb0-Paper.pdf>`_.
+            Corresponds to :math:`\\tau_0` from `'Online Learning for LDA' by Hoffman et al.`_
         passes : int, optional
             Number of passes through the corpus during training.
         update_every : int, optional

gensim/models/ldamulticore.py

@@ -38,8 +38,13 @@
 unseen documents. The model can also be updated with new documents for online training.
 
 The core estimation code is based on the `onlineldavb.py script
-<https://github.com/blei-lab/onlineldavb/blob/master/onlineldavb.py>`_, by `Hoffman, Blei, Bach:
-Online Learning for Latent Dirichlet Allocation, NIPS 2010 <http://www.cs.princeton.edu/~mdhoffma>`_.
+<https://github.com/blei-lab/onlineldavb/blob/master/onlineldavb.py>`_, by
+Matthew D. Hoffman, David M. Blei, Francis Bach:
+`'Online Learning for Latent Dirichlet Allocation', NIPS 2010`_.
+
+.. _'Online Learning for Latent Dirichlet Allocation', NIPS 2010: online-lda_
+.. _'Online Learning for LDA' by Hoffman et al.: online-lda_
+.. _online-lda: https://papers.neurips.cc/paper/2010/file/71f6278d140af599e06ad9bf1ba03cb0-Paper.pdf
 
 Usage examples
 --------------
@@ -147,13 +152,11 @@ def __init__(self, corpus=None, num_topics=100, id2word=None, workers=None,
                 * 'auto': Learns an asymmetric prior from the corpus.
         decay : float, optional
             A number between (0.5, 1] to weight what percentage of the previous lambda value is forgotten
-            when each new document is examined. Corresponds to Kappa from
-            `Matthew D. Hoffman, David M. Blei, Francis Bach:
-            "Online Learning for Latent Dirichlet Allocation NIPS'10" <https://www.di.ens.fr/~fbach/mdhnips2010.pdf>`_.
+            when each new document is examined. Corresponds to :math:`\\kappa` from
+            `'Online Learning for LDA' by Hoffman et al.`_
         offset : float, optional
             Hyper-parameter that controls how much we will slow down the first steps the first few iterations.
-            Corresponds to Tau_0 from `Matthew D. Hoffman, David M. Blei, Francis Bach:
-            "Online Learning for Latent Dirichlet Allocation NIPS'10" <https://www.di.ens.fr/~fbach/mdhnips2010.pdf>`_.
+            Corresponds to :math:`\\tau_0` from `'Online Learning for LDA' by Hoffman et al.`_
         eval_every : int, optional
             Log perplexity is estimated every that many updates. Setting this to one slows down training by ~2x.
         iterations : int, optional
@@ -198,14 +201,13 @@ def update(self, corpus, chunks_as_numpy=False):
 
         Notes
         -----
-        This update also supports updating an already trained model (`self`)
-        with new documents from `corpus`; the two models are then merged in
-        proportion to the number of old vs. new documents. This feature is still
-        experimental for non-stationary input streams.
+        This update also supports updating an already trained model (`self`) with new documents from `corpus`;
+        the two models are then merged in proportion to the number of old vs. new documents.
+        This feature is still experimental for non-stationary input streams.
 
         For stationary input (no topic drift in new documents), on the other hand,
-        this equals the online update of Hoffman et al. and is guaranteed to
-        converge for any `decay` in (0.5, 1.0>.
+        this equals the online update of `'Online Learning for LDA' by Hoffman et al.`_
+        and is guaranteed to converge for any `decay` in (0.5, 1].
 
         Parameters
         ----------