activity
20182021
most citedTuning Word2vec for Large Scale Recommendation Systems

21 citations · 34 across the 4 of their papers we have counts for

collaborators

8 papers

math.OC20211 cited

Generalized Optimization: A First Step Towards Category Theoretic Learning Theory

Dan Shiebler

The Cartesian reverse derivative is a categorical generalization of reverse-mode automatic differentiation. We use this operator to generalize several optimization algorithms, incl…

cs.LG20218 cited

Category Theory in Machine Learning

Dan Shiebler, Bruno Gavranović, Paul Wilson

Over the past two decades machine learning has permeated almost every realm of technology. At the same time, many researchers have begun using category theory as a unifying languag…

cs.IR2021

Lessons Learned Addressing Dataset Bias in Model-Based Candidate Generation at Twitter

Alim Virani, Jay Baxter, Dan Shiebler +7

Traditionally, heuristic methods are used to generate candidates for large scale recommender systems. Model-based candidate generation promises multiple potential advantages, prima…

cs.LG2021

Flattening Multiparameter Hierarchical Clustering Functors

Dan Shiebler

We bring together topological data analysis, applied category theory, and machine learning to study multiparameter hierarchical clustering. We begin by introducing a procedure for…

cs.IR202021 cited

Tuning Word2vec for Large Scale Recommendation Systems

Benjamin P. Chamberlain, Emanuele Rossi, Dan Shiebler +2

Word2vec is a powerful machine learning tool that emerged from Natural Lan-guage Processing (NLP) and is now applied in multiple domains, including recom-mender systems, forecastin…

cs.FL20204 cited

Incremental Monoidal Grammars

Dan Shiebler, Alexis Toumi, Mehrnoosh Sadrzadeh

In this work we define formal grammars in terms of free monoidal categories, along with a functor from the category of formal grammars to the category of automata. Generalising fro…