Zobrazeno 1 - 10
of 21
pro vyhledávání: '"Shiebler, Dan"'
Autor:
Shiebler, Dan
A common problem in data science is "use this function defined over this small set to generate predictions over that larger set." Extrapolation, interpolation, statistical inference and forecasting all reduce to this problem. The Kan extension is a p
Externí odkaz:
http://arxiv.org/abs/2203.09018
Autor:
Shiebler, Dan
The Cartesian reverse derivative is a categorical generalization of reverse-mode automatic differentiation. We use this operator to generalize several optimization algorithms, including a straightforward generalization of gradient descent and a novel
Externí odkaz:
http://arxiv.org/abs/2109.10262
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 language, facilitating communication between different scientific disciplines
Externí odkaz:
http://arxiv.org/abs/2106.07032
Autor:
Virani, Alim, Baxter, Jay, Shiebler, Dan, Gautier, Philip, Verma, Shivam, Xia, Yan, Sharma, Apoorv, Binnani, Sumit, Chen, Linlin, Yu, Chenguang
Traditionally, heuristic methods are used to generate candidates for large scale recommender systems. Model-based candidate generation promises multiple potential advantages, primarily that we can explicitly optimize the same objective as the downstr
Externí odkaz:
http://arxiv.org/abs/2105.09293
Autor:
Shiebler, Dan
We bring together topological data analysis, applied category theory, and machine learning to study multiparameter hierarchical clustering. We begin by introducing a procedure for flattening multiparameter hierarchical clusterings. We demonstrate tha
Externí odkaz:
http://arxiv.org/abs/2104.14734
Autor:
Shiebler, Dan
Publikováno v:
EPTCS 372, 2022, pp. 1-13
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. We first characterize manifold learning algorithms as func
Externí odkaz:
http://arxiv.org/abs/2011.07435
Autor:
Chamberlain, Benjamin P., Rossi, Emanuele, Shiebler, Dan, Sedhain, Suvash, Bronstein, Michael M.
Publikováno v:
Fourteenth ACM Conference on Recommender Systems (RecSys '20), September 22--26, 2020, Virtual Event, Brazil
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, forecasting, and network analysis. As Word2vec is often used offthe shelf, we ad
Externí odkaz:
http://arxiv.org/abs/2009.12192
Autor:
Shiebler, Dan
Publikováno v:
Compositionality, Volume 3 (2021) (April 14, 2021) compositionality:13511
In this work we take a Category Theoretic perspective on the relationship between probabilistic modeling and function approximation. We begin by defining two extensions of function composition to stochastic process subordination: one based on the co-
Externí odkaz:
http://arxiv.org/abs/2005.04735
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 from the Booleans to arbitrary semirings, we extend our construction to w
Externí odkaz:
http://arxiv.org/abs/2001.02296
Every day, hundreds of millions of new Tweets containing over 40 languages of ever-shifting vernacular flow through Twitter. Models that attempt to extract insight from this firehose of information must face the torrential covariate shift that is end
Externí odkaz:
http://arxiv.org/abs/1809.07703