arXiv:2410. 11500v2 Announce Type: replace-cross Abstract: In this paper, we establish a collection of covering number bounds for linear function classes under various norm constraints on the inputs and matrices.
arXiv:2603. 02238v2 Announce Type: replace Abstract: Length generalization is a key property of a learning algorithm that enables it to make correct predictions on inputs of any length, given finite training data.
arXiv:2609.08851v1 Announce Type: new Abstract: Recent advancements in transformer length generalization theory enable us to reliably predict when a transformer can learn to solve a task. In particul...
arXiv:2605. 22223v2 Announce Type: replace Abstract: We study how we can leverage only a handful of characteristics of a transformer's architecture to closely predict the number of different sequences it can output, both qualitatively and quantitatively.
arXiv:2606. 09731v1 Announce Type: new Abstract: We tightly characterize the VC dimension of depth-$L$ Transformers with a total of $W$ parameters, mapping an input sequence of length $T$ to a single output, establishing an upper bound of $O(L W \log (T W))$ and a nearly matching lower bound of $\Omega(L W \log (T W / L))$.
arXiv:2606. 07205v1 Announce Type: cross Abstract: The attention mechanism is a cornerstone of modern transformer architectures.
The paper examines how to allocate attention heads and head dimensions across Transformer layers to balance expressivity and efficiency. It provides a mathematical analysis of early layers’ role in information extraction and characterizes the trade‑off between head count and dimension under a fixed parameter budget. The authors prove a saturation effect of softmax activations, showing that increasing head dimensions yields diminishing returns, especially for long sequences, and propose strategies for efficient parameter allocation across layers.
arXiv:2607. 11760v1 Announce Type: new Abstract: A theoretical understanding of Transformers is crucial to better understand the capacities and limitations of large language models (LLMs).
arXiv:2507.19290v2 Announce Type: replace-cross Abstract: We study the problem of learning a structured approximation (low-rank, sparse, banded, etc.) to an unknown matrix $A$ given access to matrix-...
arXiv:2607. 18745v1 Announce Type: new Abstract: We study low-precision computation of C=AB with both factors quantized.
arXiv:2608. 12671v1 Announce Type: new Abstract: Multi-layer transformers form the critical component of essentially all large language models (LLMs) in use today.
arXiv:2608.31067v1 Announce Type: new Abstract: Learning generalizable algorithmic computations remains a challenge for neural networks, as reflected in persistent failures on compositional and lengt...
arXiv:2606. 18524v1 Announce Type: new Abstract: Looped (weight-tied) Transformers apply a shared residual block $N$ times ($h \leftarrow h + \varepsilon\,f(h)$, same $f$ at each step), increasing effective depth without adding parameters.