Transformers converge pathwise to a stochastic particle system and SPDE in the scaling limit, exhibiting synchronization by noise and exponential energy dissipation when common noise is coercive relative to self-attention drift.
A mathematical perspective on transformers.Bulletin of the American Mathematical Society, 62(3):427–479
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
years
2026 3verdicts
UNVERDICTED 3representative citing papers
The paper derives a characterization of minimax risk for KV cache compression and maps it to practical design principles and an algorithm tested on LongBench.
WassersteinGrad aggregates perturbed gradient attribution maps via their entropic Wasserstein barycenter to avoid blurring from geometric shifts in explanations of autoregressive weather forecasts.
citing papers explorer
-
Stochastic Scaling Limits and Synchronization by Noise in Deep Transformer Models
Transformers converge pathwise to a stochastic particle system and SPDE in the scaling limit, exhibiting synchronization by noise and exponential energy dissipation when common noise is coercive relative to self-attention drift.
-
The risk of KV cache compression
The paper derives a characterization of minimax risk for KV cache compression and maps it to practical design principles and an algorithm tested on LongBench.
-
Explanation of Dynamic Physical Field Predictions using WassersteinGrad: Application to Autoregressive Weather Forecasting
WassersteinGrad aggregates perturbed gradient attribution maps via their entropic Wasserstein barycenter to avoid blurring from geometric shifts in explanations of autoregressive weather forecasts.