Search Results for author:
Found 6 papers, 1 papers with code
Divide and Conquer: Hybrid Pre-training for Person Search
To the best of our knowledge, this is the first work that investigates how to support full-task pre-training using sub-task data.
Online Learning and Optimization for Queues with Unknown Demand Curve and Service Distribution
A major drawback of PTO is that its solution accuracy can often be highly sensitive to the parameter estimation errors because PTO is unable to properly link these errors (step 1) to the quality of the optimized solutions (step 2).
Grouped Adaptive Loss Weighting for Person Search
A straightforward solution is to manually assign different weights to different tasks, compensating for the diverse convergence rates.
Learning to Adapt via Latent Domains for Adaptive Semantic Segmentation
In this setting, we embed an additional pair of “latent-latent” to reduce the domain gap between the source and different latent domains, allowing the model to adapt well on multiple target domains simultaneously.
Reinforcement Learning for Volt-Var Control: A Novel Two-stage Progressive Training Strategy
In Stage 1(individual training), while holding all the other agents inactive, we separately train each agent to obtain its own optimal VVC actions in the action space: {consume, generate, do-nothing}.
An online learning approach to dynamic pricing and capacity sizing in service systems
In this work we propose an online learning framework designed for solving this problem which does not require the system's scale to increase.
