Clayton Sanford

7 papers · 2021–2025 · 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 ↓

🌍 Conference Polyglot · Bronze 🌉 Interdisciplinary Bridge · Bronze 🗺️ Taxonomy Completionist (16) 🐣 Hot Topic Early Bird 🔥 Unstoppable · Bronze

Venues

NeurIPS (5) ICML (2)

Top co-authors

Bryan Perozzi (2) Vahab Mirrokni (2) Daniel J. Hsu (2) Jonathan Halcrow (1) Ethan Hall (1) Daniel Hsu (1) Ali Behrouz (1) Matus Telgarsky (1) Mahdi Karami (1) Alberto Bietti (1)

Research topics

Machine Learning (7) Deep Learning (6) Architectures (6) Optimization & Theory · Machine Learning (6) Optimization & Theory · Deep Learning (3) Core Methods (2) Artificial Intelligence (1) Computer Science (1) Application Areas (1) Core AI (1) Foundations (1) Learning Types (1) Techniques (1)

Keywords

representation learning (2) transformer architecture (2) transformer (1) communication complexity (1) expressive power (1) theoretical analysis (1) high-dimensional features (1) dynamical system (1) chaotic dynamics (1) linear regression (1) neural network theory (1) graph connectivity (1) support vector machine (1) phase transition (1) attention mechanism (1) recurrent neural network (1) gradient flow (1) algorithmic reasoning (1) feed-forward network (1) geometric analysis (1)

Papers

Best of Both Worlds: Advantages of Hybrid Graph Sequence Models ICML 2025 Transformers, parallel computation, and logarithmic depth ICML 2024 Understanding Transformer Reasoning Capabilities via Graph Algorithms NeurIPS 2024 Representational Strengths and Limitations of Transformers NeurIPS 2023 Learning single-index models with shallow neural networks NeurIPS 2022 On Scrambling Phenomena for Randomly Initialized Recurrent Networks NeurIPS 2022 Support vector machines and linear regression coincide with very high-dimensional features NeurIPS 2021