Benjamin S Ruben retweeted
Excited to share my #NeurIPS2024 paper with @jzavatoneveth, @BenjaminSRuben, and @CPehlevan on mechanistic mismatches in data-constrained models of neural dynamics! (1/n)
Benjamin S Ruben retweeted
Nadaraya-Watson kernel smoothing as a random energy model ift.tt/5O4KdQY
Benjamin S Ruben retweeted
[1/n] Thrilled that this project with @jzavatoneveth and @cpehlevan is finally out! Our group has spent a lot of time studying high dimensional regression and its connections to scaling laws. All our results follow easily from a single central theorem 🧵
arxiv.org/abs/2405.00592
Benjamin S Ruben retweeted
Very happy to share this work in NeurIPS 2023 with @vyasnikhil96, @blake__bordelon, Sab Sainathan, @DepenKenpachi, and @CPehlevan on the consistent behavior of feature-learning networks across large widths arxiv.org/abs/2305.18411. What is large width consistency? Read on! 1/n
Benjamin S Ruben retweeted
Excited to announce that the first paper of my PhD, Long Sequence Hopfield Memory, was accepted into #NeurIPS2023!
This work was done in collaboration with @jzavatoneveth @DimaKrotov @CPehlevan1
1/
Benjamin S Ruben retweeted
Very interesting👀
The brain is a system of heterogenous ensembles. Each learner has access to a subset of the relevant information, and consensus is reached (with limited communication) across the regions.
It’s always stimulating to see good ensemble research
How can you mitigate double-descent without relying on a task-tuned regularization? In my new preprint with @CPehlevan, we show that ensembling over models of different size does the trick. (1/n)
arxiv.org/abs/2307.03176
Benjamin S Ruben retweeted
Here's a paper @CPehlevan and I wrote about neural networks that generate sequences: biorxiv.org/content/10.1101/…. Hebbian learning can store sequences as memories in neural networks for later recall. However, the tempo of the recalled sequence can differ from that of the tutor signal
Benjamin S Ruben retweeted
New @BiophysJ article! Sustained enthusiasm by @BenjaminSRuben who started this project as an undergraduate has led to this. We studied how chromosomes behave under mechanical stress by simulating their axial stretching cell.com/biophysj/fulltext/S…
Benjamin S Ruben retweeted
Celebrating the news that we had 4 papers accepted to #NeurIPS2021 and one of them is a spotlight! Congratulations and thanks to my group members @canatar_a @blake__bordelon @jzavatoneveth @TrentonBricken and Ben Ruben











