Alert button
Picture for Jennifer She

Jennifer She

Alert button

Analyzing and Improving Greedy 2-Coordinate Updates for Equality-Constrained Optimization via Steepest Descent in the 1-Norm

Jul 03, 2023
Amrutha Varshini Ramesh, Aaron Mishkin, Mark Schmidt, Yihan Zhou, Jonathan Wilder Lavington, Jennifer She

Figure 1 for Analyzing and Improving Greedy 2-Coordinate Updates for Equality-Constrained Optimization via Steepest Descent in the 1-Norm
Figure 2 for Analyzing and Improving Greedy 2-Coordinate Updates for Equality-Constrained Optimization via Steepest Descent in the 1-Norm
Figure 3 for Analyzing and Improving Greedy 2-Coordinate Updates for Equality-Constrained Optimization via Steepest Descent in the 1-Norm
Figure 4 for Analyzing and Improving Greedy 2-Coordinate Updates for Equality-Constrained Optimization via Steepest Descent in the 1-Norm

We consider minimizing a smooth function subject to a summation constraint over its variables. By exploiting a connection between the greedy 2-coordinate update for this problem and equality-constrained steepest descent in the 1-norm, we give a convergence rate for greedy selection under a proximal Polyak-Lojasiewicz assumption that is faster than random selection and independent of the problem dimension $n$. We then consider minimizing with both a summation constraint and bound constraints, as arises in the support vector machine dual problem. Existing greedy rules for this setting either guarantee trivial progress only or require $O(n^2)$ time to compute. We show that bound- and summation-constrained steepest descent in the L1-norm guarantees more progress per iteration than previous rules and can be computed in only $O(n \log n)$ time.

Viaarxiv icon

Agent-Time Attention for Sparse Rewards Multi-Agent Reinforcement Learning

Oct 31, 2022
Jennifer She, Jayesh K. Gupta, Mykel J. Kochenderfer

Figure 1 for Agent-Time Attention for Sparse Rewards Multi-Agent Reinforcement Learning

Sparse and delayed rewards pose a challenge to single agent reinforcement learning. This challenge is amplified in multi-agent reinforcement learning (MARL) where credit assignment of these rewards needs to happen not only across time, but also across agents. We propose Agent-Time Attention (ATA), a neural network model with auxiliary losses for redistributing sparse and delayed rewards in collaborative MARL. We provide a simple example that demonstrates how providing agents with their own local redistributed rewards and shared global redistributed rewards motivate different policies. We extend several MiniGrid environments, specifically MultiRoom and DoorKey, to the multi-agent sparse delayed rewards setting. We demonstrate that ATA outperforms various baselines on many instances of these environments. Source code of the experiments is available at https://github.com/jshe/agent-time-attention.

* Full version of the Extended Abstract accepted at the International Conference on Autonomous Agents and Multi-Agent Systems (AAMAS), 2022 
Viaarxiv icon

TF-GNN: Graph Neural Networks in TensorFlow

Jul 07, 2022
Oleksandr Ferludin, Arno Eigenwillig, Martin Blais, Dustin Zelle, Jan Pfeifer, Alvaro Sanchez-Gonzalez, Sibon Li, Sami Abu-El-Haija, Peter Battaglia, Neslihan Bulut, Jonathan Halcrow, Filipe Miguel Gonçalves de Almeida, Silvio Lattanzi, André Linhares, Brandon Mayer, Vahab Mirrokni, John Palowitch, Mihir Paradkar, Jennifer She, Anton Tsitsulin, Kevin Villela, Lisa Wang, David Wong, Bryan Perozzi

Figure 1 for TF-GNN: Graph Neural Networks in TensorFlow
Figure 2 for TF-GNN: Graph Neural Networks in TensorFlow
Figure 3 for TF-GNN: Graph Neural Networks in TensorFlow
Figure 4 for TF-GNN: Graph Neural Networks in TensorFlow

TensorFlow GNN (TF-GNN) is a scalable library for Graph Neural Networks in TensorFlow. It is designed from the bottom up to support the kinds of rich heterogeneous graph data that occurs in today's information ecosystems. Many production models at Google use TF-GNN and it has been recently released as an open source project. In this paper, we describe the TF-GNN data model, its Keras modeling API, and relevant capabilities such as graph sampling, distributed training, and accelerator support.

Viaarxiv icon

ETA Prediction with Graph Neural Networks in Google Maps

Aug 25, 2021
Austin Derrow-Pinion, Jennifer She, David Wong, Oliver Lange, Todd Hester, Luis Perez, Marc Nunkesser, Seongjae Lee, Xueying Guo, Brett Wiltshire, Peter W. Battaglia, Vishal Gupta, Ang Li, Zhongwen Xu, Alvaro Sanchez-Gonzalez, Yujia Li, Petar Veličković

Figure 1 for ETA Prediction with Graph Neural Networks in Google Maps
Figure 2 for ETA Prediction with Graph Neural Networks in Google Maps
Figure 3 for ETA Prediction with Graph Neural Networks in Google Maps
Figure 4 for ETA Prediction with Graph Neural Networks in Google Maps

Travel-time prediction constitutes a task of high importance in transportation networks, with web mapping services like Google Maps regularly serving vast quantities of travel time queries from users and enterprises alike. Further, such a task requires accounting for complex spatiotemporal interactions (modelling both the topological properties of the road network and anticipating events -- such as rush hours -- that may occur in the future). Hence, it is an ideal target for graph representation learning at scale. Here we present a graph neural network estimator for estimated time of arrival (ETA) which we have deployed in production at Google Maps. While our main architecture consists of standard GNN building blocks, we further detail the usage of training schedule methods such as MetaGradients in order to make our model robust and production-ready. We also provide prescriptive studies: ablating on various architectural decisions and training regimes, and qualitative analyses on real-world situations where our model provides a competitive edge. Our GNN proved powerful when deployed, significantly reducing negative ETA outcomes in several regions compared to the previous production baseline (40+% in cities like Sydney).

* To appear at CIKM 2021 (Applied Research Track). 10 pages, 4 figures 
Viaarxiv icon

Adversarial Computation of Optimal Transport Maps

Jun 24, 2019
Jacob Leygonie, Jennifer She, Amjad Almahairi, Sai Rajeswar, Aaron Courville

Figure 1 for Adversarial Computation of Optimal Transport Maps
Figure 2 for Adversarial Computation of Optimal Transport Maps
Figure 3 for Adversarial Computation of Optimal Transport Maps
Figure 4 for Adversarial Computation of Optimal Transport Maps

Computing optimal transport maps between high-dimensional and continuous distributions is a challenging problem in optimal transport (OT). Generative adversarial networks (GANs) are powerful generative models which have been successfully applied to learn maps across high-dimensional domains. However, little is known about the nature of the map learned with a GAN objective. To address this problem, we propose a generative adversarial model in which the discriminator's objective is the $2$-Wasserstein metric. We show that during training, our generator follows the $W_2$-geodesic between the initial and the target distributions. As a consequence, it reproduces an optimal map at the end of training. We validate our approach empirically in both low-dimensional and high-dimensional continuous settings, and show that it outperforms prior methods on image data.

Viaarxiv icon