Nicholas Teague

Published in From the Diaries of John Henry

·Pinned

Book 6: Endurance

From the Diaries of John Henry — Introduction It is hard to ponder back on the essays of Book 6 without considering their context. The pandemic was gradually being retracted in the mainstream dialogue as vaccine sourced immunity started to contribute, albeit it would be hard to characterize any boundary of success as with this progress viral variants…

Machine Learning

9 min read

Published in From the Diaries of John Henry

·Aug 12

Global Minima

Data types matter — One Looking back on the ICML conference, one of the eye opening takeaways to this author was actually associated with no more than a brief comment by a presenter. In Weinan E’s keynote Towards a Mathematical Theory of Machine Learning, he shared a slide commenting on the global minima of a…

Machine Learning

3 min read

Published in Automunge

·Aug 5

Validations with Automunge

Stable version release 8.29 — Looking back, the Automunge development process I think was somewhat unique in the field for the sheer pace of iterative developments throughout the multi-year span of focus. It is not unsurprising that in this context the interest of a user base was not exactly what I would consider as compounding…

Machine Learning

4 min read

Published in From the Diaries of John Henry

·Aug 2

A Conformal Predictions Workshop

Distribution-Free Uncertainty Quantification #ICML2022 — Distribution-Free Uncertainty Quantification Workshop Presented at the International Conference on Machine Learning held in Baltimore, MD on July 23, 2022. Workshop Home Page Organizers: Anastasios Angelopoulos (UC Berkely) · Stephen Bates (UC Berkely) · Sharon Yixuan Li (UW Madison) · Ryan Tibshirani (CMU) · Aaditya Ramdas (CMU)

Conformal Prediction

22 min read

Published in From the Diaries of John Henry

·Jul 2

The Best of Vision

#CVPR2022 “unofficial” poster awards —

Computer Vision

35 min read

Published in From the Diaries of John Henry

·Jun 29

Dimensional Framings of Overparameterization

Getting from geometric regularization to double descent — Part 1 — Geometric Regularization from Overparameterization Background This essay is meant to document some of the author’s more recent musings on subject of the geometric regularization conjecture, which was a novel (and somewhat speculative) framing of emergent regularization properties that may arise from overparameterized models, explored in some depth in the paper Geometric Regularization from Overparameterization Explains…

Deep Learning

36 min read

Dimensional Framings of Overparameterization

Published in From the Diaries of John Henry

·Jun 27

Over Teaguey

Always look on the sunny side of life — I think I invented a new way to cook an egg. Similar to over easy, but the moment before flipping you slightly puncture yolk with the corner of spatula. Results in maintained yolk coherence, but without liquid center. Better on sandwiches. “Over Teaguey” Ingredients Two eggs Pita bread (optionally gluten free) …

Recipe

2 min read

Published in From the Diaries of John Henry

·Jun 23

Vision for All Seasons

#CVPR2022 “Unofficial” Workshop Minutes — Opening Remarks The following represent an unofficial meeting minutes of sorts, recording the discussions presented at the IEEE Computer Vision and Pattern Recognition — Vision for All Season Workshop. I recorded these notes as an attendee and given how good the workshop turned out wanted to share with the community as a…

Machine Learning

20 min read

Published in From the Diaries of John Henry

·Jun 21

Denoising Diffusion-Based Generative Modeling

#CVPR2022 Tutorial “Unofficial” Minutes — The following essay represents an unofficial meeting minutes of sorts, recording (at a high level) the discussions presented at the IEEE Computer Vision and Pattern Recognition Conference Denoising Diffusion-based Generative Modeling: Foundations and Applications Tutorial. (Yes I know that is a mouthfull, it took me like two whole minutes to…

Machine Learning

10 min read

Denoising Diffusion-Based Generative Modeling

Published in Automunge

·Jun 14

DataPerf ML with Automunge

ICML 2022, DataPerf Workshop — The following presentation is based on the paper Stochastic Perturbations of Tabular Features for Non-Deterministic Inference with Automunge, to be presented at the ICML 2022 DataPerf workshop. We welcome inquiries and opportunities, contact is available at automunge.com. Stochastic Perturbations of Tabular Features for Non-Deterministic Inference With Automungenicholasteague.medium.com

Machine Learning

4 min read