paper-with-me

Papers

Trading Complexity for Expressivity Through Structured Generalized Linear Token Mixing

2026-05-29 · Erwan Fagnou, Paul Caillon, Blaise Delattre, Alexandre Allauzen arxiv

Token mixing layers play a key role in how language models can learn and generate long-range dependencies. Their efficiency relies on the necessary trade-off between decoding speed and the memory requirements, along with the cache size. Considering causal generation, this paper explores new trade-offs thanks to a unified framework which separates two crucial features: (i) the direct influence of inputs on outputs in one generation step; (ii) the recurrent propagation of information through past outputs. This framework encompasses major architectures such as attention and state-space models, but also generalizes the recurrence equations by allowing each state to depend on multiple past states rather than only the immediate predecessor. By introducing structure, we design new recurrence patterns that provably achieve the desired complexity, while providing theoretical insights on their expressivity -- trading runtime for expressivity in a principled way. Empirical validation is performed on synthetic tasks, along with language modeling. Together, these results provide a unified toolkit for the understanding and design of efficient and expressive token mixers across model families.

📄 PDF Abstract BibTeX arXiv:2605.31367

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

From Scaling to Structured Expressivity: Rethinking Transformers for CTR Prediction

2025-11-15 · Bencheng Yan, Yuejie Lei, Zhiyuan Zeng, Zheye Deng 외 arxiv

Despite massive investments in scale, deep models for click-through rate (CTR) prediction often exhibit rapidly diminishing returns -- a stark contrast to the {predictable scaling laws} seen in large language models (LLM…

The Generalized Skew Spectrum of Graphs

2025-05-29 · Armando Bellante, Martin Plávala, Alessandro Luongo

This paper proposes a family of permutation-invariant graph embeddings, generalizing the Skew Spectrum of graphs of Kondor & Borgwardt (2008). Grounded in group theory and harmonic analysis, our method introduces a new c…

Flash PD-SSM: Memory-Optimized Structured Sparse State-Space Models

2026-05-18 · Aleksandar Terzić, Francesco Carzaniga, Nicolas Menet, Yannick Biehl 외 arxiv

State-space models (SSMs) face a fundamental trade-off between efficiency and expressivity that is mainly dictated by the structure of the model's transition matrix. Unstructured transition matrices enable maximal expres…

Graph Representational Learning: When Does More Expressivity Hurt Generalization?

2025-05-16 · Sohir Maskey, Raffaele Paolino, Fabian Jogl, Gitta Kutyniok 외

Graph Neural Networks (GNNs) are powerful tools for learning on structured data, yet the relationship between their expressivity and predictive performance remains unclear. We introduce a family of premetrics that captur…

Generalization Bounds

Towards Bridging Generalization and Expressivity of Graph Neural Networks

2024-10-14 · Shouheng Li, Floris Geerts, Dongwoo Kim, Qing Wang

Expressivity and generalization are two critical aspects of graph neural networks (GNNs). While significant progress has been made in studying the expressivity of GNNs, much less is known about their generalization capab…