921 citations · 9.3k across the 292 of their papers we have counts for
18 papers · 2 filters
Stackelberg GAN: Towards Provable Minimax Equilibrium via Multi-Generator Architectures
Hongyang Zhang, Susu Xu, Jiantao Jiao +3
We study the problem of alleviating the instability issue in the GAN training procedure via new architecture design. The discrepancy between the minimax and maximin objective value…
On the Complexity of Exploration in Goal-Driven Navigation
Maruan Al-Shedivat, Lisa Lee, Ruslan Salakhutdinov +1
Building agents that can explore their environments intelligently is a challenging open problem. In this paper, we make a step towards understanding how a hierarchical design of th…
Connecting the Dots Between MLE and RL for Sequence Prediction
Bowen Tan, Zhiting Hu, Zichao Yang +2
Sequence prediction models can be learned from example sequences with a variety of training algorithms. Maximum likelihood learning is simple and efficient, yet can suffer from com…
Fault Tolerance in Iterative-Convergent Machine Learning
Aurick Qiao, Bryon Aragam, Bingjing Zhang +1
Machine learning (ML) training algorithms often possess an inherent self-correcting behavior due to their iterative-convergent nature. Recent systems exploit this property to achie…
Toward Understanding the Impact of Staleness in Distributed Machine Learning
Wei Dai, Yi Zhou, Nanqing Dong +2
Many distributed machine learning (ML) systems adopt the non-synchronous execution in order to alleviate the network communication bottleneck, resulting in stale parameters that do…
AutoLoss: Learning Discrete Schedules for Alternate Optimization
Haowen Xu, Hao Zhang, Zhiting Hu +3
Many machine learning problems involve iteratively and alternately optimizing different task objectives with respect to different sets of parameters. Appropriately scheduling the o…