Record · danmackinlay.name

Why does deep learning work? – The Dan MacKinlay stable of variably-well-consider’d enterprises

Dan MacKinlay · 1 October 2026 · 6 min read

A post on danmackinlay.name, published 1 October 2026, has not been cited by any blog yet (corpus.blog, measured 12 October 2026).

A record is what was published and who pointed at it. The text of the post is not shown here: read it at the source, or at its Wayback capture.

Read at danmackinlay.name Wayback capture

0blogs citing

Citing blogs and links by period
Period	Blogs	Links
All time	0	0
Last 90 days	0	0
Last 30 days	0	0
Last 7 days	0	0

Figures for this page
Words blogs link it with	0
External links	42
Length	1,289

Cited by

No blog we hold has cited this post yet.

Links from this post

Link

Host

ML Theory with bad drawings Read at windowsontheory.org

windowsontheory.org

https://mjt.cs.illinois.edu/dlt/

mjt.cs.illinois.edu

https://mjt.cs.illinois.edu/dlt/index.pdf?ref=danmackinlay.name

mjt.cs.illinois.edu

https://mcallester.github.io/ttic-31230/Fall2020/?ref=danmackinlay.name

mcallester.github.io

https://bair.berkeley.edu/blog/2017/08/31/saddle-efficiency/?ref=danmackinlay.name

bair.berkeley.edu

https://www.offconvex.org/2016/03/22/saddlepoints/ Who cites this page

offconvex.org

http://www.offconvex.org/2016/03/24/saddles-again/?ref=danmackinlay.name

offconvex.org

http://noahgolmant.com/avoiding-saddle-points.html?ref=danmackinlay.name

noahgolmant.com

https://www.microsoft.com/en-us/research/blog/a-deep-learning-theory-global-minima-and-over-parameterization/?ref=danmackinlay.name

microsoft.com

https://www.youtube.com/watch?v=5MdSE-N0bxs&ref=danmackinlay.name

youtube.com

https://www.quantamagazine.org/20141204-a-common-logic-to-seeing-cats-and-cosmos?ref=danmackinlay.name

quantamagazine.org

Why Deep Learning Works II: the Renormalization Group Read at calculatedcontent.com

calculatedcontent.com

Autopsy of a deep learning paper Read at blog.piekniewski.info

blog.piekniewski.info

https://learningmechanics.pub/about/?ref=danmackinlay.name

learningmechanics.pub

https://udlbook.github.io/udlbook/ Who cites this page

udlbook.github.io

Gradient Dissent Read at betterwithout.ai

betterwithout.ai

https://predictive-optimization.cs.princeton.edu/ Who cites this page

predictive-optimization.cs.princeton.edu

https://doi.org/10.1017/S0962492921000027

doi.org

http://proceedings.mlr.press/v97/belilovsky19a.html

proceedings.mlr.press

https://doi.org/10.1017/9781009025096.002

doi.org

https://doi.org/10.1137/18M118709X

doi.org

https://proceedings.mlr.press/v38/choromanska15.html Who cites this page

proceedings.mlr.press

https://arxiv.org/abs/1406.2572 Who cites this page

arxiv.org

https://doi.org/10.1109/TIT.2021.3062161

doi.org

http://arxiv.org/abs/1712.06541

arxiv.org

https://doi.org/10.1088/1361-6420/aa9a90

doi.org

http://proceedings.mlr.press/v70/jin17a.html

proceedings.mlr.press

https://arxiv.org/abs/1710.05468 Who cites this page

arxiv.org

https://arxiv.org/abs/1710.07406 Who cites this page

arxiv.org

https://arxiv.org/abs/1602.04915 Who cites this page

arxiv.org

https://arxiv.org/abs/1608.08225 Who cites this page

arxiv.org

https://arxiv.org/abs/2006.15191 Who cites this page

arxiv.org

https://doi.org/10.23915/distill.00007 Who cites this page

doi.org

http://arxiv.org/abs/1405.4604

arxiv.org

https://doi.org/10.1007/s10851-019-00903-1

doi.org

http://arxiv.org/abs/1412.6615

arxiv.org

http://arxiv.org/abs/1707.04615

arxiv.org

http://arxiv.org/abs/1802.09210

arxiv.org

http://arxiv.org/abs/1512.06293

arxiv.org

https://doi.org/10.1109/TIT.2017.2756880

doi.org

http://arxiv.org/abs/1611.03131

arxiv.org

https://arxiv.org/abs/1611.03530 Who cites this page

arxiv.org

Elsewhere on danmackinlay.name (13)

Neural nets – The Dan MacKinlay stable of variably-well-consider’d enterprises Read at danmackinlay.name

danmackinlay.name

Compressing neural nets – The Dan MacKinlay stable of variably-well-consider’d enterprises Read at danmackinlay.name

danmackinlay.name

Overparameterization in large models – The Dan MacKinlay stable of variably-well-consider’d enterprises Read at danmackinlay.name

danmackinlay.name

Statistical mechanics of statistics and NNs – The Dan MacKinlay stable of variably-well-consider’d enterprises Read at danmackinlay.name

danmackinlay.name

Markov Chain Monte Carlo methods – The Dan MacKinlay stable of variably-well-consider’d enterprises Read at danmackinlay.name

danmackinlay.name

Ensembling neural nets – The Dan MacKinlay stable of variably-well-consider’d enterprises Read at danmackinlay.name

danmackinlay.name

(Reproducing) kernel tricks – The Dan MacKinlay stable of variably-well-consider’d enterprises Read at danmackinlay.name

danmackinlay.name

Singular Learning Theory – The Dan MacKinlay stable of variably-well-consider’d enterprises Read at danmackinlay.name

danmackinlay.name

Deep linear networks – The Dan MacKinlay stable of variably-well-consider’d enterprises Read at danmackinlay.name

danmackinlay.name

Function approximation and interpolation – The Dan MacKinlay stable of variably-well-consider’d enterprises Read at danmackinlay.name

danmackinlay.name

Function space versus weight space in Neural Nets – The Dan MacKinlay stable of variably-well-consider’d enterprises Read at danmackinlay.name

danmackinlay.name

Deep learning as a dynamical system – The Dan MacKinlay stable of variably-well-consider’d enterprises Read at danmackinlay.name

danmackinlay.name

Validating and reproducing science – The Dan MacKinlay stable of variably-well-consider’d enterprises Read at danmackinlay.name

danmackinlay.name

Why does deep learning work? – The Dan MacKinlay stable of variably-well-consider’d enterprises

Cited by

Links from this post

Similar posts