InfoFlow: A Framework for Multi-Layer Transformer Analysis

• URL: http://arxiv.org/abs/2605.17930v1
• Date: Mon, 18 May 2026 06:38:39 GMT
• Title: InfoFlow: A Framework for Multi-Layer Transformer Analysis
• Abstract summary: Multi-layer Transformers possess fundamentally different approximation capabilities from single-layer ones.<n>We propose InfoFlow, a framework for multi-layer Transformers.
• Score: 28.731784494689276
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: While the approximation properties of single-layer Transformer architectures have been studied in recent works, a rigorous theoretical understanding of the multi-layer setting remains limited. In this work, we establish that multi-layer Transformers possess fundamentally different approximation capabilities from single-layer ones: for certain retrieval tasks, any single-layer Transformer requires least $Ω(\varepsilon^{-k})$ parameters to achieve precision $\varepsilon$, where $k$ grows linearly with sequence length $T$, whereas a two-layer Transformer with a single head per layer achieves the same approximation precision with at most $O (\varepsilon^{-1})$ parameters. To understand this separation, we identify two structural mechanisms underlying multi-layer approximation. Specifically, softmax attention can only efficiently retrieve the token attaining the maximum attention score, incurring exponential-in-length parameter cost for $k$-th largest retrieval with $k \geq 2$. Moreover, the parameter cost of decoding coupled information scales with the size of the retrieved token set. Motivated by these findings, we propose InfoFlow, a framework for multi-layer Transformers. The framework tracks an information set of accessible input positions at each token and layer, assigning an explicit approximation rate to each mode of information propagation. This abstraction recovers known approximation bounds, remains consistent with experimental observations on trained networks, and yields concrete predictions in settings where direct theoretical analysis is currently intractable. Our results provide a principled framework for reasoning about the approximation efficiency of multi-layer Transformers.

Related papers

• Transformers Provably Learn to Internalize Chain-of-Thought [65.41010769606844]
  Implicit Chain-of-Thought (ICoT) trains models to internalize intermediate steps within their hidden states.<n>Log-ICoT removes thinking tokens one at a time, reducing the number of stages from linear in $k$ to logarithmic.<n>Experiments on multi-layer transformers confirm the theory and visualize how reasoning is progressively absorbed into deeper layers.
  arXiv  Detail & Related papers  (2026-05-27T15:17:06Z)
• Learning Theory of Transformers: Local-to-Global Approximation via Softmax Partition of Unity [5.37133760455631]
  This paper investigates the learning theory of Transformer networks for regression tasks on the compact Euclidean domain $[0,1]d$.<n>We propose a novel constructive approximation framework for Transformers that builds local approximations of the target function and aggregates them into a global approximation.<n>We prove that a dense Transformer equipped with only two encoder blocks and standard single-hidden-layer point-wise feed-forward networks can achieve a uniform $varepsilon$-approximation error for $$-Hlder continuous functions.
  arXiv  Detail & Related papers  (2026-05-09T09:02:37Z)
• The Recurrent Transformer: Greater Effective Depth and Efficient Decoding [48.9323408950142]
  We introduce the Recurrent Transformer, a simple architectural change where each layer attends to key-value pairs computed off its own activations.<n>We show that the architecture can emulate both (i) a conventional Transformer and (ii) token-to-gressive recurrent updates under mild assumptions.
  arXiv  Detail & Related papers  (2026-04-23T02:12:58Z)
• The Effect of Attention Head Count on Transformer Approximation [26.943083432025926]
  We study the approximation properties of transformers, with particular emphasis on the role of the number of attention heads.<n>Specifically, we show that transformers with sufficiently many heads admit efficient approximation, whereas with too few heads, the number of parameters must scale at least as $O(1/epsiloncT)$, for some constant $c$ and sequence length $T$.
  arXiv  Detail & Related papers  (2025-10-08T05:27:25Z)
• Approximation Bounds for Transformer Networks with Application to Regression [9.549045683389085]
  We explore the approximation capabilities of Transformer networks for H"older and Sobolev functions.<n>We establish novel upper bounds for standard Transformer networks approxing sequence-to-sequence mappings.<n>We show that if the self-attention layer in a Transformer can perform column averaging, the network can approximate sequence-to-sequence H"older functions.
  arXiv  Detail & Related papers  (2025-04-16T15:25:58Z)
• Kronecker-Factored Approximate Curvature for Modern Neural Network Architectures [85.76673783330334]
  Two different settings of linear weight-sharing layers motivate two flavours of Kronecker-Factored Approximate Curvature (K-FAC) We show they are exact for deep linear networks with weight-sharing in their respective setting. We observe little difference between these two K-FAC variations when using them to train both a graph neural network and a vision transformer.
  arXiv  Detail & Related papers  (2023-11-01T16:37:00Z)
• Transformers as Support Vector Machines [54.642793677472724]
  We establish a formal equivalence between the optimization geometry of self-attention and a hard-margin SVM problem. We characterize the implicit bias of 1-layer transformers optimized with gradient descent. We believe these findings inspire the interpretation of transformers as a hierarchy of SVMs that separates and selects optimal tokens.
  arXiv  Detail & Related papers  (2023-08-31T17:57:50Z)
• Universality and Limitations of Prompt Tuning [65.8354898840308]
  We take one of the first steps to understand the role of soft-prompt tuning for transformer-based architectures. We analyze prompt tuning from the lens of universality and limitations with finite-depth pretrained transformers for continuous-valued functions. Our result guarantees the existence of a strong transformer with a prompt to approximate any sequence-to-sequence function in the set of Lipschitz functions.
  arXiv  Detail & Related papers  (2023-05-30T06:47:07Z)
• $O(n)$ Connections are Expressive Enough: Universal Approximability of Sparse Transformers [71.31712741938837]
  We show that sparse Transformers with only $O(n)$ connections per attention layer can approximate the same function class as the dense model with $n2$ connections. We also present experiments comparing different patterns/levels of sparsity on standard NLP tasks.
  arXiv  Detail & Related papers  (2020-06-08T18:30:12Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.