🏢 Penn State University
The Surprising Effectiveness of SP Voting with Partial Preferences
·3640 words·18 mins·
loading
·
loading
AI Theory
Optimization
🏢 Penn State University
Partial preferences and noisy votes hinder accurate ranking recovery; this paper introduces scalable SP voting variants, empirically demonstrating superior performance in recovering ground truth ranki…
Putting Gale & Shapley to Work: Guaranteeing Stability Through Learning
·1809 words·9 mins·
loading
·
loading
AI Theory
Optimization
🏢 Penn State University
Researchers improve two-sided matching market algorithms by prioritizing stability through novel bandit-learning algorithms, providing theoretical bounds on sample complexity and demonstrating intrigu…
Non-asymptotic Convergence of Training Transformers for Next-token Prediction
·361 words·2 mins·
loading
·
loading
AI Generated
AI Theory
Optimization
🏢 Penn State University
This paper reveals how a one-layer transformer’s training converges for next-token prediction, showing sub-linear convergence for both layers and shedding light on its surprising generalization abilit…