6 citations · 9 across the 14 of their papers we have counts for
8 papers · 1 filter
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…
Synchronization of mean-field models on the circle
Yury Polyanskiy, Philippe Rigollet, Andrew Yao
This paper considers a mean-field model of interacting particles whose state space is the unit circle, a generalization of the classical Kuramoto model. Global synchronization…
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…
Partial and Exact Recovery of a Random Hypergraph from its Graph Projection
Guy Bresler, Chenghao Guo, Yury Polyanskiy +1
Consider a -uniform random hypergraph on vertices in which hyperedges are included iid so that the average degree is . The projection of a hypergraph is a graph on the…
Thresholds for Reconstruction of Random Hypergraphs From Graph Projections
Guy Bresler, Chenghao Guo, Yury Polyanskiy
The graph projection of a hypergraph is a simple graph with the same vertex set and with an edge between each pair of vertices that appear in a hyperedge. We consider the problem o…
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…