Clayton Sanford
7 papers · 2021–2025 · 2 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+1 more ↓ Show less ↑
π Interdisciplinary Bridge π§ Keyword Pioneer π Conference Polyglot (2) π Cross-Pollinator (13) πΊοΈ Taxonomy Completionist (12)
π₯
Unstoppable
(5)
Conferences
NIPS (5)
ICML (2)
Top co-authors
Keywords
transformer architecture
(2)
representation learning
(2)
geometric analysis
(1)
attention mechanism
(1)
communication complexity
(1)
theoretical analysis
(1)
neural network theory
(1)
high-dimensional features
(1)
chaotic dynamics
(1)
linear regression
(1)
expressive power
(1)
graph connectivity
(1)
support vector machine
(1)
phase transition
(1)
dynamical system
(1)
recurrent neural network
(1)
gradient flow
(1)
algorithmic reasoning
(1)
shallow neural network
(1)
feedforward network
(1)
Papers
Best of Both Worlds: Advantages of Hybrid Graph Sequence Models
ICML 2025
Understanding Transformer Reasoning Capabilities via Graph Algorithms
NIPS 2024
Transformers, parallel computation, and logarithmic depth
ICML 2024
Representational Strengths and Limitations of Transformers
NIPS 2023
On Scrambling Phenomena for Randomly Initialized Recurrent Networks
NIPS 2022
Learning single-index models with shallow neural networks
NIPS 2022
Support vector machines and linear regression coincide with very high-dimensional features
NIPS 2021