Alan Jeffares
@alanjeffares.bsky.social
Multiplying matrices @Cambridge_Uni & @MSFTResearch | PhD student in Machine Learning | Previously MSc @ucl & BSc @ucddublin
alanjeffares.com
alanjeffares.com
Pinned
Alan Jeffares
@alanjeffares.bsky.social
· Nov 17
and all of a sudden, my feed changed from musk and outrage to matrices and optimisers…
me trying to cut my ICML rebuttal down to <5000 characters
March 31, 2025 at 12:17 PM
me trying to cut my ICML rebuttal down to <5000 characters
If people knew how much of my PhD has consisted of reading about something new, referencing back to Elements of Statistical Learning, and simply writing down what I learned…
It feels like a cheat code!
It feels like a cheat code!
btw this is why friends dont let friends skip the “boring classical ML” chapters in Elements of Statistical Learning‼️
(True story: the origin of this case study is that @alanjeffares.bsky.social[big EoSL nerd] looked at the neural net eq&said “kinda looks like GBTs in EoSL Ch10”&we went from there)
(True story: the origin of this case study is that @alanjeffares.bsky.social[big EoSL nerd] looked at the neural net eq&said “kinda looks like GBTs in EoSL Ch10”&we went from there)
but WAIT A MINUTE — isn’t that literally the same formula as the kernel representation of the telescoping model of a trained neural network I showed you before?? Just with a different kernel??
Surely this diff in kernel must account for at least some of the observed performance differences… 🤔7/n
Surely this diff in kernel must account for at least some of the observed performance differences… 🤔7/n
November 20, 2024 at 9:44 PM
If people knew how much of my PhD has consisted of reading about something new, referencing back to Elements of Statistical Learning, and simply writing down what I learned…
It feels like a cheat code!
It feels like a cheat code!
Reposted by Alan Jeffares
Part 2: Why do boosted trees outperform deep learning on tabular data??
@alanjeffares.bsky.social & I suspected that answers to this are obfuscated by the 2 being considered very different algs🤔
Instead we show they are more similar than you’d think — making their diffs smaller but predictive!🧵1/n
@alanjeffares.bsky.social & I suspected that answers to this are obfuscated by the 2 being considered very different algs🤔
Instead we show they are more similar than you’d think — making their diffs smaller but predictive!🧵1/n
November 20, 2024 at 5:02 PM
Part 2: Why do boosted trees outperform deep learning on tabular data??
@alanjeffares.bsky.social & I suspected that answers to this are obfuscated by the 2 being considered very different algs🤔
Instead we show they are more similar than you’d think — making their diffs smaller but predictive!🧵1/n
@alanjeffares.bsky.social & I suspected that answers to this are obfuscated by the 2 being considered very different algs🤔
Instead we show they are more similar than you’d think — making their diffs smaller but predictive!🧵1/n
i’m too lazy to make a thinly-veiled self-promotion “starter pack”, so if you could all add me anyway that would be great…
November 19, 2024 at 4:27 PM
i’m too lazy to make a thinly-veiled self-promotion “starter pack”, so if you could all add me anyway that would be great…
Reposted by Alan Jeffares
From double descent to grokking, deep learning sometimes works in unpredictable ways.. or does it?
For NeurIPS(my final PhD paper!), @alanjeffares.bsky.social & I explored if&how smart linearisation can help us better understand&predict numerous odd deep learning phenomena — and learned a lot..🧵1/n
For NeurIPS(my final PhD paper!), @alanjeffares.bsky.social & I explored if&how smart linearisation can help us better understand&predict numerous odd deep learning phenomena — and learned a lot..🧵1/n
November 18, 2024 at 7:25 PM
From double descent to grokking, deep learning sometimes works in unpredictable ways.. or does it?
For NeurIPS(my final PhD paper!), @alanjeffares.bsky.social & I explored if&how smart linearisation can help us better understand&predict numerous odd deep learning phenomena — and learned a lot..🧵1/n
For NeurIPS(my final PhD paper!), @alanjeffares.bsky.social & I explored if&how smart linearisation can help us better understand&predict numerous odd deep learning phenomena — and learned a lot..🧵1/n
and all of a sudden, my feed changed from musk and outrage to matrices and optimisers…
November 17, 2024 at 5:27 PM
and all of a sudden, my feed changed from musk and outrage to matrices and optimisers…