6 citations · 9 across the 14 of their papers we have counts for
9 papers · 1 filter
YuriiFormer: A Suite of Nesterov-Accelerated Transformers
Aleksandr Zimin, Yury Polyanskiy, Philippe Rigollet
We propose a variational framework that interprets transformer layers as iterations of an optimization algorithm acting on token embeddings. In this view, self-attention implements…
Normalization in Attention Dynamics
Nikita Karagodin, Shu Ge, Yury Polyanskiy +1
We study the effect of normalization schemes on token representations in deep transformers. Modeling their evolution as interacting particles on the sphere, we show that normalizat…
Critical attention scaling in long-context transformers
Shi Chen, Zhengjiang Lin, Yury Polyanskiy +1
As large language models scale to longer contexts, attention layers suffer from a fundamental pathology: attention scores collapse toward uniformity as context length increases…
Global Minimizers of Sigmoid Contrastive Loss
Kiril Bangachev, Guy Bresler, Iliyas Noman +1
The meta-task of obtaining and aligning representations through contrastive pretraining is steadily gaining importance since its introduction in CLIP and ALIGN. In this paper we th…
Quantitative Clustering in Mean-Field Transformer Models
Shi Chen, Zhengjiang Lin, Yury Polyanskiy +1
The evolution of tokens through deep transformer models can be modeled as an interacting particle system that has been shown to exhibit an asymptotic clustering behavior akin to th…
Residual connections provably mitigate oversmoothing in graph neural networks
Ziang Chen, Zhengjiang Lin, Shi Chen +2
Graph neural networks (GNNs) have achieved remarkable empirical success in processing and representing graph-structured data across various domains. However, a significant challeng…
Clustering in Causal Attention Masking
Nikita Karagodin, Yury Polyanskiy, Philippe Rigollet
This work presents a modification of the self-attention dynamics proposed by Geshkovski et al. (arXiv:2312.10794) to better reflect the practically relevant, causally masked attent…
Dynamic metastability in the self-attention model
Borjan Geshkovski, Hugo Koubbi, Yury Polyanskiy +1
We consider the self-attention model - an interacting particle system on the unit sphere, which serves as a toy model for Transformers, the deep neural network architecture behind…
A mathematical perspective on Transformers
Borjan Geshkovski, Cyril Letrouit, Yury Polyanskiy +1
Transformers play a central role in the inner workings of large language models. We develop a mathematical framework for analyzing Transformers based on their interpretation as int…