Haijie Gu — accepted AI-conference papers

2026

Towards Safe and Optimal Online Bidding: A Modular Look-ahead Lyapunov Framework

Hengquan Guo, Haobo Zhang, Junwei Pan, Shudong Huang, Nianhua Xie, Lei Xiao +3

ICLR 2026poster

This paper studies online bidding subject to simultaneous budget and return-on-investment (ROI) constraints, which encodes the goal of balancing high volume and profitability. We formulate the problem as a general constrained online learning problem that can be applied to diverse bidding settings (e…

Cited by 0 Source ↗Scholar ↗

2020

AdaScale SGD: A User-Friendly Algorithm for Distributed Training

Tyler Johnson, Pulkit Agrawal, Haijie Gu, Carlos Guestrin

ICML 2020poster

When using large-batch training to speed up stochastic gradient descent, learning rates must adapt to new batch sizes in order to maximize speed-ups and preserve model quality. Re-tuning learning rates is resource intensive, while fixed scaling rules often degrade model quality. We propose AdaScale…

Cited by 38 Source ↗PDF ↗Scholar ↗