MultiBalance: Multi-Objective Gradient Balancing in Industrial-Scale Multi-Task Recommendation System

no code implementations • 3 Nov 2024 • Yun He, Xuxing Chen, Jiayi Xu, Renqin Cai, Yiling You, Jennifer Cao, Minhui Huang, Liu Yang, Yiqun Liu, Xiaoyi Liu, Rong Jin, Sem Park, Bo Long, Xue Feng

In industrial recommendation systems, multi-task learning (learning multiple tasks simultaneously on a single model) is a predominant approach to save training/serving resources and improve recommendation performance via knowledge transfer between the joint learning tasks.

Multi-Task Learning Recommendation Systems

Traffic Control via Connected and Automated Vehicles: An Open-Road Field Experiment with 100 CAVs

no code implementations • 26 Feb 2024 • Jonathan W. Lee, Han Wang, Kathy Jang, Amaury Hayat, Matthew Bunting, Arwa Alanqary, William Barbour, Zhe Fu, Xiaoqian Gong, George Gunter, Sharon Hornstein, Abdul Rahman Kreidieh, Nathan Lichtlé, Matthew W. Nice, William A. Richardson, Adit Shah, Eugene Vinitsky, Fangyu Wu, Shengquan Xiang, Sulaiman Almatrudi, Fahd Althukair, Rahul Bhadani, Joy Carpio, Raphael Chekroun, Eric Cheng, Maria Teresa Chiri, Fang-Chieh Chou, Ryan Delorenzo, Marsalis Gibson, Derek Gloudemans, Anish Gollakota, Junyi Ji, Alexander Keimer, Nour Khoudari, Malaika Mahmood, Mikail Mahmood, Hossein Nick Zinat Matin, Sean McQuade, Rabie Ramadan, Daniel Urieli, Xia Wang, Yanbing Wang, Rita Xu, Mengsha Yao, Yiling You, Gergely Zachár, Yibo Zhao, Mostafa Ameli, Mirza Najamuddin Baig, Sarah Bhaskaran, Kenneth Butts, Manasi Gowda, Caroline Janssen, John Lee, Liam Pedersen, Riley Wagner, Zimo Zhang, Chang Zhou, Daniel B. Work, Benjamin Seibold, Jonathan Sprinkle, Benedetto Piccoli, Maria Laura Delle Monache, Alexandre M. Bayen

The upper layer is called Speed Planner, and is a centralized optimal control algorithm.

Model Predictive Control

Limitations and Improvements of the Intelligent Driver Model (IDM)

no code implementations • 2 Apr 2021 • Saleh Albeaik, Alexandre Bayen, Maria Teresa Chiri, Xiaoqian Gong, Amaury Hayat, Nicolas Kardous, Alexander Keimer, Sean T. McQuade, Benedetto Piccoli, Yiling You

First it is shown that, for a specific class of initial data, the vehicles' velocities become negative or even diverge to $-\infty$ in finite time, both undesirable properties for a car-following model.