Image de couverture de livre

The Expressive Power of Transformers with Chain of Thought

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Merrill, William, Sabharwal, Ashish
Format:	Preprint
Publié:	2023
Sujets:	Machine Learning Computational Complexity Computation and Language Logic in Computer Science
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Exact Expressive Power of Transformers with Padding
par: Merrill, William, et autres
Publié: (2025)

A Little Depth Goes a Long Way: The Expressive Power of Log-Depth Transformers
par: Merrill, William, et autres
Publié: (2025)

Revisiting Padded Transformer Expressivity: Which Architectural Choices Matter and Which Don't
par: Svete, Anej, et autres
Publié: (2026)

A Logic for Expressing Log-Precision Transformers
par: Merrill, William, et autres
Publié: (2022)

The Illusion of State in State-Space Models
par: Merrill, William, et autres
Publié: (2024)

The Expressive Power of Low Precision Softmax Transformers with (Summarized) Chain-of-Thought
par: Brösamle, Moritz, et autres
Publié: (2026)

Why Are Linear RNNs More Parallelizable?
par: Merrill, William, et autres
Publié: (2026)

The Complexity and Expressive Power of Second-Order Extended Logic
par: Feng, Shiguang, et autres
Publié: (2022)

The Descriptive Complexity of Graph Neural Networks
par: Grohe, Martin
Publié: (2023)

Local vs. Global Interpretability: A Computational Complexity Perspective
par: Bassan, Shahaf, et autres
Publié: (2024)

On the Computational Tractability of the (Many) Shapley Values
par: Marzouk, Reda, et autres
Publié: (2025)

Hard to Explain: On the Computational Hardness of In-Distribution Model Interpretation
par: Amir, Guy, et autres
Publié: (2024)

Verifying Quantized Graph Neural Networks is PSPACE-complete
par: Sälzer, Marco, et autres
Publié: (2025)

Provably Explaining Neural Additive Models
par: Bassan, Shahaf, et autres
Publié: (2026)

Is uniform expressivity too restrictive? Towards efficient expressivity of graph neural networks
par: Khalife, Sammy, et autres
Publié: (2024)

What makes an Ensemble (Un) Interpretable?
par: Bassan, Shahaf, et autres
Publié: (2025)

The Complexity of Verifying Feedforward Neural Networks in Quantised Settings
par: Alsmann, Eric, et autres
Publié: (2026)

Limits of Deep Learning: Sequence Modeling through the Lens of Complexity Theory
par: Zubić, Nikola, et autres
Publié: (2024)

Transformer Encoder Satisfiability: Complexity and Impact on Formal Reasoning
par: Sälzer, Marco, et autres
Publié: (2024)

Kleene algebra with commutativity conditions is undecidable
par: de Amorim, Arthur Azevedo, et autres
Publié: (2024)

What Formal Languages Can Transformers Express? A Survey
par: Strobl, Lena, et autres
Publié: (2023)

The Power of Negation in Higher-Order Datalog
par: Charalambidis, Angelos, et autres
Publié: (2025)

Reasonable Space for the $λ$-Calculus, Logarithmically
par: Accattoli, Beniamino, et autres
Publié: (2022)

LFPL: Revisited and Mechanized
par: Glover, Nathaniel, et autres
Publié: (2026)

Complete and tractable machine-independent characterizations of second-order polytime
par: Hainry, Emmanuel, et autres
Publié: (2022)

Reversible Computation with Stacks and "Reversible Management of Failures"
par: Palazzo, Matteo, et autres
Publié: (2025)

Program Synthesis is $Σ_3^0$-Complete
par: Kim, Jinwoo
Publié: (2024)

The Reachability Problem for Neural-Network Control Systems
par: Schilling, Christian, et autres
Publié: (2024)

The Computational Complexity of Satisfiability in State Space Models
par: Alsmann, Eric, et autres
Publié: (2025)

Verifying Quantized GNNs With Readout Is Decidable But Highly Intractable
par: Chernobrovkin, Artem, et autres
Publié: (2025)

Data Complexity in Expressive Description Logics With Path Expressions
par: Bednarczyk, Bartosz
Publié: (2024)

Primitive Recursion without Composition: Dynamical Characterizations, from Neural Networks to Polynomial ODEs
par: Bournez, Olivier
Publié: (2026)

Theoretical Constraints on the Expressive Power of $\mathsf{RoPE}$-based Tensor Attention Transformers
par: Li, Xiaoyu, et autres
Publié: (2024)

Context-Free Recognition with Transformers
par: Jerad, Selim, et autres
Publié: (2026)

Non-commutative linear logic fragments with sub-context-free complexity
par: Nishimiya, Yusaku, et autres
Publié: (2025)

An order out of nowhere: a new algorithm for infinite-domain CSPs
par: Mottet, Antoine, et autres
Publié: (2023)

Functional variant of Polynomial Analogue of Gandy's Fixed Point Theorem
par: Nechesov, Andrey
Publié: (2024)

Proof Complexity of Linear Logics
par: Tabatabai, Amirhossein Akbar, et autres
Publié: (2026)

The Proof Analysis Problem
par: Arteche, Noel, et autres
Publié: (2025)

Proof complexity of positive branching programs
par: Das, Anupam, et autres
Publié: (2021)