Adrián Javaloy
@javaloyml.bsky.social
Postdoc at the University of Edinburgh working on Machine Learning. Previously in Saarbrücken, Tübingen, and Murcia.
🌐 adrianjav.github.io
🌐 adrianjav.github.io
PS: If something, just check it out for the aesthetics 😋 (I will release the LaTeX template soon)
publikationen.sulb.uni-saarland.de/handle/20.50...
🧵4/4
publikationen.sulb.uni-saarland.de/handle/20.50...
🧵4/4
Publikationen der UdS: Meet my expectations: on the interplay of trustworthiness and deep learning optimization
publikationen.sulb.uni-saarland.de
August 6, 2025 at 7:57 PM
PS: If something, just check it out for the aesthetics 😋 (I will release the LaTeX template soon)
publikationen.sulb.uni-saarland.de/handle/20.50...
🧵4/4
publikationen.sulb.uni-saarland.de/handle/20.50...
🧵4/4
Funny enough, I later found my perspective on soft constraints to be quite similar as that of soft inductive biases by @andrewgwils.bsky.social in one of his latest works:
arxiv.org/abs/2503.02113
🧵3/4
arxiv.org/abs/2503.02113
🧵3/4
Deep Learning is Not So Mysterious or Different
Deep neural networks are often seen as different from other model classes by defying conventional notions of generalization. Popular examples of anomalous generalization behaviour include benign overf...
arxiv.org
August 6, 2025 at 7:57 PM
Funny enough, I later found my perspective on soft constraints to be quite similar as that of soft inductive biases by @andrewgwils.bsky.social in one of his latest works:
arxiv.org/abs/2503.02113
🧵3/4
arxiv.org/abs/2503.02113
🧵3/4
Also, I did put considerably effort to frame everything under a common question:
> What biases can we add to DL optimization so that the outcome of the model is what we expected from the beginning?
🧵2/4
> What biases can we add to DL optimization so that the outcome of the model is what we expected from the beginning?
🧵2/4
August 6, 2025 at 7:57 PM
Also, I did put considerably effort to frame everything under a common question:
> What biases can we add to DL optimization so that the outcome of the model is what we expected from the beginning?
🧵2/4
> What biases can we add to DL optimization so that the outcome of the model is what we expected from the beginning?
🧵2/4
That would be awesome!
FYI The rule was different two months ago, requiring only virtual attendance, and it was changed during the reviewing period.
web.archive.org/web/20250514...
FYI The rule was different two months ago, requiring only virtual attendance, and it was changed during the reviewing period.
web.archive.org/web/20250514...
Papers
web.archive.org
July 18, 2025 at 8:13 AM
That would be awesome!
FYI The rule was different two months ago, requiring only virtual attendance, and it was changed during the reviewing period.
web.archive.org/web/20250514...
FYI The rule was different two months ago, requiring only virtual attendance, and it was changed during the reviewing period.
web.archive.org/web/20250514...
Reposted by Adrián Javaloy
Hmm, this rule seems very recently changed? web.archive.org/web/20250514...
This was what it said just before the deadline, so people submitting to NeurIPS couldn't have known about the mandatory physical presence 🤔
This was what it said just before the deadline, so people submitting to NeurIPS couldn't have known about the mandatory physical presence 🤔
July 17, 2025 at 2:16 PM
Hmm, this rule seems very recently changed? web.archive.org/web/20250514...
This was what it said just before the deadline, so people submitting to NeurIPS couldn't have known about the mandatory physical presence 🤔
This was what it said just before the deadline, so people submitting to NeurIPS couldn't have known about the mandatory physical presence 🤔