Subquadratic Algorithms and Hardness for Attention with Any Temperature
Fuente:
arXiv
Saved in:
| Main Authors: | Gupta, Shreya, Huang, Boyang, Saha, Barna, Xu, Yinzhan, Ye, Christopher |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Similar Items
On the Computational Hardness of Transformers
by: Saha, Barna, et al.
Published: (2026)
by: Saha, Barna, et al.
Published: (2026)
Fine-Grained Optimality of Partially Dynamic Shortest Paths and More
by: Saha, Barna, et al.
Published: (2024)
by: Saha, Barna, et al.
Published: (2024)
Algorithmic hardness of the partition function for nucleic acid strands
by: Ducloz, Gwendal, et al.
Published: (2025)
by: Ducloz, Gwendal, et al.
Published: (2025)
The Banach-Butterfly Invariant: Influence-Adaptive Walsh Geometry for Ternary Polynomial Threshold Functions
by: Pavlov, Gorgi
Published: (2026)
by: Pavlov, Gorgi
Published: (2026)
The Structural Complexity of Matrix-Vector Multiplication
by: Anand, Emile, et al.
Published: (2025)
by: Anand, Emile, et al.
Published: (2025)
The I/O Complexity of Attention, or How Optimal is Flash Attention?
by: Saha, Barna, et al.
Published: (2024)
by: Saha, Barna, et al.
Published: (2024)
Polynomial-time Tractable Problems over the $p$-adic Numbers
by: Fehm, Arno, et al.
Published: (2025)
by: Fehm, Arno, et al.
Published: (2025)
The Bit Complexity of Dynamic Algebraic Formulas and their Determinants
by: Anand, Emile, et al.
Published: (2024)
by: Anand, Emile, et al.
Published: (2024)
Small Shadow Partitions
by: Kopparty, Swastik, et al.
Published: (2024)
by: Kopparty, Swastik, et al.
Published: (2024)
On Sampling Lower Bounds for Polynomials
by: Khodabandeh, Mohammad Mahdi, et al.
Published: (2026)
by: Khodabandeh, Mohammad Mahdi, et al.
Published: (2026)
PosSLP and Sum of Squares
by: Bläser, Markus, et al.
Published: (2024)
by: Bläser, Markus, et al.
Published: (2024)
Average Attention Transformers and Arithmetic Circuits
by: Ehrmuth, Lena, et al.
Published: (2026)
by: Ehrmuth, Lena, et al.
Published: (2026)
Symmetric Arithmetic Circuits
by: Dawar, Anuj, et al.
Published: (2020)
by: Dawar, Anuj, et al.
Published: (2020)
Lower Bounds for Symmetric Circuits for the Determinant
by: Dawar, Anuj, et al.
Published: (2021)
by: Dawar, Anuj, et al.
Published: (2021)
When Votes Change and Committees Should (Not)
by: Bredereck, Robert, et al.
Published: (2020)
by: Bredereck, Robert, et al.
Published: (2020)
Col is PSPACE-complete on Triangular Grids
by: Burke, Kyle, et al.
Published: (2025)
by: Burke, Kyle, et al.
Published: (2025)
The Simultaneous Triple Product Property and Group-theoretic Results for the Exponent of Matrix Multiplication
by: Murthy, Sandeep
Published: (2007)
by: Murthy, Sandeep
Published: (2007)
On the Computation of 2-Dimensional Recurrence Equations
by: Natale, Giuseppe
Published: (2024)
by: Natale, Giuseppe
Published: (2024)
Completeness classes in algebraic complexity theory
by: Bürgisser, Peter
Published: (2024)
by: Bürgisser, Peter
Published: (2024)
Graph Colouring Is Hard on Average for Polynomial Calculus and Nullstellensatz
by: Conneryd, Jonas, et al.
Published: (2025)
by: Conneryd, Jonas, et al.
Published: (2025)
Clique Is Hard on Average for Sherali-Adams with Bounded Coefficients
by: de Rezende, Susanna F., et al.
Published: (2024)
by: de Rezende, Susanna F., et al.
Published: (2024)
Eliminating Illusion in Directed Networks
by: Jana, Sougata, et al.
Published: (2026)
by: Jana, Sougata, et al.
Published: (2026)
Realizable Circuit Complexity: Embedding Computation in Space-Time
by: Prada, Benjamin, et al.
Published: (2025)
by: Prada, Benjamin, et al.
Published: (2025)
Graph Neural Networks and Arithmetic Circuits
by: Barlag, Timon, et al.
Published: (2024)
by: Barlag, Timon, et al.
Published: (2024)
Recurrent Graph Neural Networks and Arithmetic Circuits
by: Barlag, Timon, et al.
Published: (2026)
by: Barlag, Timon, et al.
Published: (2026)
Replicability in High Dimensional Statistics
by: Hopkins, Max, et al.
Published: (2024)
by: Hopkins, Max, et al.
Published: (2024)
Fundamental Limitations on Subquadratic Alternatives to Transformers
by: Alman, Josh, et al.
Published: (2024)
by: Alman, Josh, et al.
Published: (2024)
Complete Decomposition of Symmetric Tensors in Linear Time and Polylogarithmic Precision
by: Koiran, Pascal, et al.
Published: (2022)
by: Koiran, Pascal, et al.
Published: (2022)
Beyond Worst-Case Subset Sum: An Adaptive, Structure-Aware Solver with Sub-$2^{n/2}$ Enumeration
by: Salas, Jesus
Published: (2025)
by: Salas, Jesus
Published: (2025)
Misère Partizan Arc Kayles is PSPACE-complete, even on Planar Graphs
by: Burke, Kyle, et al.
Published: (2025)
by: Burke, Kyle, et al.
Published: (2025)
Dichotomy for orderings?
by: Kun, Gábor, et al.
Published: (2025)
by: Kun, Gábor, et al.
Published: (2025)
Shifted Partial Derivative Polynomial Rank and Codimension
by: Edwards, Darren J.
Published: (2025)
by: Edwards, Darren J.
Published: (2025)
Near-Optimal Bootstrapping of Hitting Sets for Algebraic Models
by: Kumar, Mrinal, et al.
Published: (2018)
by: Kumar, Mrinal, et al.
Published: (2018)
Lower Bounds for Chain-of-Thought Reasoning in Hard-Attention Transformers
by: Amiri, Alireza, et al.
Published: (2025)
by: Amiri, Alireza, et al.
Published: (2025)
Low-Bandwidth Matrix Multiplication: Faster Algorithms and More General Forms of Sparsity
by: Gupta, Chetan, et al.
Published: (2024)
by: Gupta, Chetan, et al.
Published: (2024)
Matrix-by-matrix multiplication algorithm with $O(N^2log_2N)$ computational complexity for variable precision arithmetic
by: Paszyński, Maciej
Published: (2024)
by: Paszyński, Maciej
Published: (2024)
IECZ-III: Hardcore Condensation Lift with Size-Aware Invariants
by: Lela, Marko
Published: (2025)
by: Lela, Marko
Published: (2025)
Two-Sided Lossless Expanders in the Unbalanced Setting
by: Chattopadhyay, Eshan, et al.
Published: (2024)
by: Chattopadhyay, Eshan, et al.
Published: (2024)
Implementation of Polynomial NP-Complete Algorithms Based on the NP Verifier Simulation Framework
by: Lee, Changryeol
Published: (2026)
by: Lee, Changryeol
Published: (2026)
Decoding Rewards in Competitive Games: Inverse Game Theory with Entropy Regularization
by: Liao, Junyi, et al.
Published: (2026)
by: Liao, Junyi, et al.
Published: (2026)
Similar Items
-
On the Computational Hardness of Transformers
by: Saha, Barna, et al.
Published: (2026) -
Fine-Grained Optimality of Partially Dynamic Shortest Paths and More
by: Saha, Barna, et al.
Published: (2024) -
Algorithmic hardness of the partition function for nucleic acid strands
by: Ducloz, Gwendal, et al.
Published: (2025) -
The Banach-Butterfly Invariant: Influence-Adaptive Walsh Geometry for Ternary Polynomial Threshold Functions
by: Pavlov, Gorgi
Published: (2026) -
The Structural Complexity of Matrix-Vector Multiplication
by: Anand, Emile, et al.
Published: (2025)