IEEE

Aggregated Conditional Gradient Method for Decentralized Constrained Learning from Non-IID Data

Abstract: Decentralized learning is a distributed learning approach, wherein clients collaborate to learn a global model. Many optimization problems that appear in signal processing and machine ...
IEEE

Learning Expert-Level Racing Strategies via Scheduled Cost Functions in Model Predictive Control

Abstract: In racing sports, driving strategies necessitate meticulous control and optimal utilization of vehicle dynamics. Model predictive control (MPC) has emerged as an effective approach for ...
GitHub

SQL-R1: Training Natural Language to SQL Reasoning Model By Reinforcement Learning

Natural Language to SQL (NL2SQL) enables intuitive interactions with databases by transforming natural language queries into structured SQL statements. Despite recent advancements in enhancing ...
Mises Institute

Brazil’s Social Function Trap: When Property Becomes Conditional, Markets Become Political

Brazil is often described as a constitutional democracy with a market economy: You can buy a home, start a business, sign contracts, and sue in court. Yet many Brazilians live with a quieter reality: ...