Suhas Kotha

Hello! I am a PhD student at Stanford, interested in improving machine learning by understanding where it fails. I previously studied CS at CMU, fortunate to be advised by Aditi Raghunathan.

Papers Selected Complete

Content

Fresh work/ideas

• Optimal Experimental Design with Compute Constraints
• Highest Likelihood Decoding
• 💜 Lower Diversity Accelerates Convergence for Regression
• 💜 Synthesizing Optimal Parallel Collectives via SAT
• The Type Theory of Transformers

Challenges

• Language Data Ordering and Filtering
• 💜 Emergence as Prediction Across Scale

Paper Analyses

• Transformers are RNNs
• Provable Guarantees for Self-Supervised Deep Learning with Spectral Contrastive Loss
• A Universal Law of Robustness via Isoperimetry

Introductions

• Second Law of Thermodynamics
• Elegance of Linear Regression
• Understanding Reinforcement Learning from Human Feedback
• Convex Geometry for Computers