Image de couverture de livre

A Logic for Expressing Log-Precision Transformers

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Merrill, William, Sabharwal, Ashish
Format:	Preprint
Publié:	2022
Sujets:	Machine Learning Computational Complexity
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

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

The Expressive Power of Transformers with Chain of Thought
par: Merrill, William, et autres
Publié: (2023)

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

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

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

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

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

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

On the Computational Hardness of Transformers
par: Saha, Barna, et autres
Publié: (2026)

Constant Bit-size Transformers Are Turing Complete
par: Li, Qian, et autres
Publié: (2025)

Lower Bounds for Chain-of-Thought Reasoning in Hard-Attention Transformers
par: Amiri, Alireza, et autres
Publié: (2025)

Chain of Thought Empowers Transformers to Solve Inherently Serial Problems
par: Li, Zhiyuan, et autres
Publié: (2024)

Rethinking the Role of Positional Encoding: Sliding-Window Transformers without PE Remain Turing Complete
par: Li, Qian, et autres
Publié: (2026)

Fundamental Limitations on Subquadratic Alternatives to Transformers
par: Alman, Josh, et autres
Publié: (2024)

Provable Failure of Language Models in Learning Majority Boolean Logic via Gradient Descent
par: Chen, Bo, et autres
Publié: (2025)

Provably Overwhelming Transformer Models with Designed Inputs
par: Stambler, Lev, et autres
Publié: (2025)

Additive Models Explained: A Computational Complexity Approach
par: Bassan, Shahaf, et autres
Publié: (2025)

Fundamental Limits of Crystalline Equivariant Graph Neural Networks: A Circuit Complexity Perspective
par: Cao, Yang, et autres
Publié: (2025)

Computational Limits of Low-Rank Adaptation (LoRA) Fine-Tuning for Transformer Models
par: Hu, Jerry Yao-Chieh, et autres
Publié: (2024)

How Much Cache Does Reasoning Need? Depth-Cache Tradeoffs in KV-Compressed Transformers
par: Wang, Xiao
Publié: (2026)

Learning Tree Pattern Transformations
par: Neider, Daniel, et autres
Publié: (2024)

Efficient Turing Machine Simulation with Transformers
par: Li, Qian, et autres
Publié: (2025)

Reachability In Simple Neural Networks
par: Sälzer, Marco, et autres
Publié: (2022)

On the Hardness of Learning Regular Expressions
par: Attias, Idan, et autres
Publié: (2025)

Learnability of Parameter-Bounded Bayes Nets
par: Bhattacharyya, Arnab, et autres
Publié: (2024)

How Hard Is Continuous Clustering? Lower Bounds from the Existential Theory of the Reals
par: Majumdar, Angshul
Publié: (2026)

Spiky Rank and Its Applications to Rigidity and Circuits
par: Hambardzumyan, Lianna, et autres
Publié: (2026)

Low-Rank Matrix Approximation for Neural Network Compression
par: Cherukuri, Kalyan, et autres
Publié: (2025)

Proximity to Losslessly Compressible Parameters
par: Farrugia-Roberts, Matthew
Publié: (2023)

Decision Tree Learning on Product Spaces
par: Moakahr, Arshia Soltani, et autres
Publié: (2026)

Statistical and Computational Guarantees of Kernel Max-Sliced Wasserstein Distances
par: Wang, Jie, et autres
Publié: (2024)

Smoothed Analysis for Learning Concepts with Low Intrinsic Dimension
par: Chandrasekaran, Gautam, et autres
Publié: (2024)

Optimizing Computational-Statistical Runtime for Wasserstein Distance Estimation
par: Jacobs, Peter Matthew, et autres
Publié: (2026)

Distribution-Specific Agnostic Conditional Classification With Halfspaces
par: Huang, Jizhou, et autres
Publié: (2025)

From Pseudorandomness to Multi-Group Fairness and Back
par: Dwork, Cynthia, et autres
Publié: (2023)

Ask, and it shall be given: On the Turing completeness of prompting
par: Qiu, Ruizhong, et autres
Publié: (2024)

Necessary and Sufficient Oracles: Toward a Computational Taxonomy For Reinforcement Learning
par: Rohatgi, Dhruv, et autres
Publié: (2025)

How Global Calibration Strengthens Multiaccuracy
par: Casacuberta, Sílvia, et autres
Publié: (2025)

Diffusion Language Models are Provably Optimal Parallel Samplers
par: Jiang, Haozhe, et autres
Publié: (2025)

Certifiable Boolean Reasoning Is Universal
par: Li, Wenhao, et autres
Publié: (2026)