The Library

A curated index of foundational papers — the texts that defined how we think about data, models, and the uneasy boundary between statistics and machine learning. Read the originals. Form your own view.

"Without data, you're just another person with an opinion."

— W. Edwards Deming

[2] Papers in the Reading Room

Ref. 2001

Statistical Modeling: The Two Cultures

Leo BreimanStatistical Science

Recommended Reading

The paper that named the tension this platform is built on. Breiman argues — with evidence — that the statistical community's near-exclusive commitment to data models has produced irrelevant theory and missed the algorithmic revolution. Read this first.

There are two cultures in the use of statistical modeling to reach conclusions from data. One assumes that the data are generated by a given stochastic data model. The other uses algorithmic models and treats the data mechanism as unknown. The statistical community has been committed to the almost exclusive use of data models. This commitment has led to irrelevant theory, questionable conclusions, and has kept statisticians from working on a large range of interesting current problems. Algorithmic modeling, both in theory and practice, has developed rapidly in fields outside statistics. It can be used both on large complex data sets and as a more accurate and informative alternative to data modeling on smaller data sets. If our goal as a field is to use data to solve problems, then we need to move away from exclusive dependence on data models and adopt a more diverse set of tools.

#modeling#machine-learning#philosophy#prediction

Examine Paper External Source

Ref. 2017

Attention Is All You Need

Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N. Gomez, Łukasz Kaiser, Illia PolosukhinNeurIPS

The architectural paper that Breiman's argument predicted. Where 'Two Cultures' diagnosed the divide between data models and algorithmic thinking, this paper built the most consequential algorithm of the algorithmic era. The two papers form a diptych.

The dominant sequence transduction models are based on complex recurrent or convolutional neural networks that include an encoder and a decoder. The best performing models also connect the encoder and decoder through an attention mechanism. We propose a new simple network architecture, the Transformer, based solely on attention mechanisms, dispensing with recurrence and convolutions entirely. Experiments on two machine translation tasks show these models to be superior in quality while being more parallelizable and requiring significantly less time to train. Our model achieves 28.4 BLEU on the WMT 2014 English-to-German translation task, improving over the existing best results, including ensembles, by over 2 BLEU. On the WMT 2014 English-to-French translation task, our model establishes a new single-model state-of-the-art BLEU score of 41.8 after training for 3.5 days on eight GPUs, a small fraction of the training costs of the best models from the literature. We show that the Transformer generalizes well to other tasks by applying it successfully to English constituency parsing both with large and limited training data.

#deep-learning#transformers#attention#nlp

Examine Paper External Source