Salvato in:
Dettagli Bibliografici
Autori principali: Ruscio, Valeria, Nanni, Umberto, Silvestri, Fabrizio
Natura: Preprint
Pubblicazione: 2024
Soggetti:
Accesso online:https://arxiv.org/abs/2410.18067
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866908393853157376
author Ruscio, Valeria
Nanni, Umberto
Silvestri, Fabrizio
author_facet Ruscio, Valeria
Nanni, Umberto
Silvestri, Fabrizio
contents This paper studies how Transformer models with Rotary Position Embeddings (RoPE) develop emergent, wavelet-like properties that compensate for the positional encoding's theoretical limitations. Through an analysis spanning model scales, architectures, and training checkpoints, we show that attention heads evolve to implement multi-resolution processing analogous to wavelet transforms. We demonstrate that this scale-invariant behavior is unique to RoPE, emerges through distinct evolutionary phases during training, and statistically adheres to the fundamental uncertainty principle. Our findings suggest that the effectiveness of modern Transformers stems from their remarkable ability to spontaneously develop optimal, multi-resolution decompositions to address inherent architectural constraints.
format Preprint
id arxiv_https___arxiv_org_abs_2410_18067
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Beyond Position: the emergence of wavelet-like properties in Transformers
Ruscio, Valeria
Nanni, Umberto
Silvestri, Fabrizio
Machine Learning
Artificial Intelligence
This paper studies how Transformer models with Rotary Position Embeddings (RoPE) develop emergent, wavelet-like properties that compensate for the positional encoding's theoretical limitations. Through an analysis spanning model scales, architectures, and training checkpoints, we show that attention heads evolve to implement multi-resolution processing analogous to wavelet transforms. We demonstrate that this scale-invariant behavior is unique to RoPE, emerges through distinct evolutionary phases during training, and statistically adheres to the fundamental uncertainty principle. Our findings suggest that the effectiveness of modern Transformers stems from their remarkable ability to spontaneously develop optimal, multi-resolution decompositions to address inherent architectural constraints.
title Beyond Position: the emergence of wavelet-like properties in Transformers
topic Machine Learning
Artificial Intelligence
url https://arxiv.org/abs/2410.18067