Josh Alman
6 papers · 2023–2025 · 2 venues · across top CS/AI venues
Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.
Achievements
Jump to papers ↓
π
Conference Polyglot Β· Bronze
π
Interdisciplinary Bridge Β· Silver
πΊοΈ
Taxonomy Completionist
(19)
π
Keyword Champion
(2)
β
The Questioner
Venues
Top co-authors
Research topics
Machine Learning
(5)
Deep Learning
(4)
Optimization & Theory Β· Machine Learning
(3)
Techniques
(3)
Artificial Intelligence
(2)
Mathematics & Optimization
(2)
Application Areas
(2)
Architectures
(2)
Core AI
(2)
Optimization
(2)
Optimization & Theory Β· Deep Learning
(2)
Natural Language Processing
(1)
Core Methods
(1)
Mathematics
(1)
Resources & Methods
(1)
Keywords
attention mechanism
(3)
computational complexity
(2)
fine-grained complexity
(2)
subquadratic time
(2)
theoretical analysis
(1)
computational efficiency
(1)
training optimization
(1)
low-rank approximation
(1)
low-rank matrix
(1)
gradient computation
(1)
kronecker product
(1)
algorithm complexity
(1)
complexity bound
(1)
matrix computation
(1)
state space model
(1)
tensor computation
(1)
linear algebra
(1)
preprocessing algorithm
(1)
positive definite kernel
(1)
manhattan distance
(1)
Papers
Fundamental Limitations on Subquadratic Alternatives to Transformers
ICLR 2025
How to Capture Higher-order Correlations? Generalizing Matrix Softmax Attention to Kronecker Computation
ICLR 2024
Metric Transforms and Low Rank Representations of Kernels for Fast Attention
NeurIPS 2024
The Fine-Grained Complexity of Gradient Computation for Training Large Language Models
NeurIPS 2024
Bypass Exponential Time Preprocessing: Fast Neural Network Training via Weight-Data Correlation Preprocessing
NeurIPS 2023
Fast Attention Requires Bounded Entries
NeurIPS 2023