Cover Image

Strassen Attention, Split VC Dimension and Compositionality in Transformers

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Kozachinskiy, Alexander, Urrutia, Felipe, Jimenez, Hector, Steifer, Tomasz, Pizarro, Germán, Fuentes, Matías, Meza, Francisco, Calderon, Cristian B., Rojas, Cristóbal
Format:	Preprint
Published:	2025
Subjects:	Machine Learning Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Decoupling Positional and Symbolic Attention Behavior in Transformers
by: Urrutia, Felipe, et al.
Published: (2025)

Simple online learning with consistent oracle
by: Kozachinskiy, Alexander, et al.
Published: (2023)

A completely uniform transformer for parity
by: Kozachinskiy, Alexander, et al.
Published: (2025)

Effective Littlestone Dimension
by: Rose, Valentino Delle, et al.
Published: (2024)

Parity, Sensitivity, and Transformers
by: Kozachinskiy, Alexander, et al.
Published: (2026)

Continuity and Isolation Lead to Doubts or Dilemmas in Large Language Models
by: Pasten, Hector, et al.
Published: (2025)

Optimal bounds for dissatisfaction in perpetual voting
by: Kozachinskiy, Alexander, et al.
Published: (2024)

Ehrenfeucht-Haussler Rank and Chain of Thought
by: Barceló, Pablo, et al.
Published: (2025)

Provably Shorter Scratchpads in Hybrid DeltaNet-Attention Decoders
by: Steifer, Tomasz
Published: (2026)

On dimensionality of feature vectors in MPNNs
by: Bravo, César, et al.
Published: (2024)

Computable universal online learning
by: Kalociński, Dariusz, et al.
Published: (2025)

Positional versus Symbolic Attention Heads: Learning Dynamics, RoPE Geometry, and Length Generalization
by: Urrutia, Felipe, et al.
Published: (2026)

Lower bounds on transformers with infinite precision
by: Kozachinskiy, Alexander
Published: (2024)

Dvorak-Dell-Grohe-Rattan theorem via an asymptotic argument
by: Kozachinskiy, Alexander
Published: (2025)

Continuous Positional Payoffs
by: Kozachinskiy, Alexander
Published: (2020)

Learning Equivalence Relations on Polish Spaces
by: Rossegger, Dino, et al.
Published: (2024)

Three iterations of $(d-1)$-WL test distinguish non isometric clouds of $d$-dimensional points
by: Rose, Valentino Delle, et al.
Published: (2023)

Propiedades ópticas, comportamiento de flujo y dureza de geles basados en nanoemulsión
by: Cristóbal Rojas-Pizarro
Published: (2024)

Message Passing on the Edge: Towards Scalable and Expressive GNNs
by: Barceló, Pablo, et al.
Published: (2025)

The work of Leslie Valiant: alle die Strassen führen nach Strassen
by: J. Andrés Montoya
Published: (2014)

All Kolmogorov complexity functions are optimal, but are some more optimal?
by: Bauwens, Bruno, et al.
Published: (2025)

The No-Clash Teaching Dimension is Bounded by VC Dimension
by: Liu, Jiahua, et al.
Published: (2026)

String Dimension: VC Dimension for Infinite Shattering
by: Ryan-Smith, Calliope
Published: (2024)

The Counting Power of Transformers
by: Sälzer, Marco, et al.
Published: (2025)

Strassen's algorithm is not optimally accurate
by: Dumas, Jean-Guillaume, et al.
Published: (2024)

On Strassen's Theorem for support functions
by: Schrott, Stefan, et al.
Published: (2023)

The Parameterized Complexity of Computing the VC-Dimension
by: Foucaud, Florent, et al.
Published: (2025)

Contradiction Graphs Determine VC Dimension
by: Campbell, Jesse, et al.
Published: (2026)

Practical Computation of Graph VC-Dimension
by: Coudert, David, et al.
Published: (2024)

Denkmäler der römischen Straßen in Ungarn
by: Bödőcs, András
Published: (2026)

Amphimallon montanum Zur Strassen 1954
by: Sparacio, Ignazio, et al.
Published: (2025)

Denkmäler der römischen Straßen in Ungarn
by: Bödőcs, András
Published: (2026)

Faster Convolutions: Yates and Strassen Revisited
by: Brand, Cornelius, et al.
Published: (2025)

Strassen's theorem for biased convex order
by: Acciaio, Beatrice, et al.
Published: (2025)

Strassen Multisystolic Array Hardware Architectures
by: Pogue, Trevor E., et al.
Published: (2025)

Deep Natural Language Feature Learning for Interpretable Prediction
by: Urrutia, Felipe, et al.
Published: (2023)

Networks with Finite VC Dimension: Pro and Contra
by: Kurkova, Vera, et al.
Published: (2025)

A nonlinear Strassen law for singular SPDEs
by: Parekh, Shalin
Published: (2023)

Strassen's support functionals coincide with the quantum functionals
by: Sakabe, Keiya, et al.
Published: (2026)

Strassen's algorithm via orbit flip graphs
by: Ikenmeyer, Christian, et al.
Published: (2025)