no code implementations • 17 Mar 2022 • Dan Shiebler
A common problem in data science is "use this function defined over this small set to generate predictions over that larger set."
no code implementations • 20 Sep 2021 • Dan Shiebler
The Cartesian reverse derivative is a categorical generalization of reverse-mode automatic differentiation.
no code implementations • 13 Jun 2021 • Dan Shiebler, Bruno Gavranović, Paul Wilson
Over the past two decades machine learning has permeated almost every realm of technology.
no code implementations • 13 May 2021 • Alim Virani, Jay Baxter, Dan Shiebler, Philip Gautier, Shivam Verma, Yan Xia, Apoorv Sharma, Sumit Binnani, LinLin Chen, Chenguang Yu
Traditionally, heuristic methods are used to generate candidates for large scale recommender systems.
1 code implementation • 30 Apr 2021 • Dan Shiebler
We bring together topological data analysis, applied category theory, and machine learning to study multiparameter hierarchical clustering.
no code implementations • 15 Nov 2020 • Dan Shiebler
We adapt previous research on category theory and topological unsupervised learning to develop a functorial perspective on manifold learning, also known as nonlinear dimensionality reduction.
no code implementations • NeurIPS Workshop TDA_and_Beyond 2020 • Dan Shiebler
We adapt previous research on topological unsupervised learning to characterize hierarchical overlapping clustering algorithms as functors that factor through a category of simplicial complexes.
no code implementations • 24 Sep 2020 • Benjamin P. Chamberlain, Emanuele Rossi, Dan Shiebler, Suvash Sedhain, Michael M. Bronstein
We show that applying constrained hy-perparameter optimization using only a 10% sample of the data still yields a 91%average improvement in hit rate over the default parameters when applied to thefull datasets.
1 code implementation • 10 May 2020 • Dan Shiebler
In this work we take a Category Theoretic perspective on the relationship between probabilistic modeling and function approximation.
no code implementations • 2 Jan 2020 • 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.
no code implementations • ICLR 2019 • Drew Linsley, Dan Shiebler, Sven Eberhardt, Thomas Serre
Most recent gains in visual recognition have originated from the inclusion of attention mechanisms in deep convolutional networks (DCNs).
no code implementations • 18 Sep 2018 • Dan Shiebler, Luca Belli, Jay Baxter, Hanchen Xiong, Abhishek Tayal
Every day, hundreds of millions of new Tweets containing over 40 languages of ever-shifting vernacular flow through Twitter.
no code implementations • 10 Sep 2018 • Dan Shiebler
Although modern recommendation systems can exploit the structure in users' item feedback, most are powerless in the face of new users who provide no structure for them to exploit.
1 code implementation • 22 May 2018 • Drew Linsley, Dan Shiebler, Sven Eberhardt, Thomas Serre
Most recent gains in visual recognition have originated from the inclusion of attention mechanisms in deep convolutional networks (DCNs).