674 citations
Counting papers with at most 25 authors, so collaboration author lists do not stand in for the people here.
- University of Illinois ChicagoUS13 papers
- Singapore Management UniversitySG11 papers
- Carnegie Mellon UniversityUS8 papers
- Georgia Institute of TechnologyUS7 papers
- Princeton UniversityUS7 papers
- Nanyang Technological UniversitySG6 papers
- University of Illinois Urbana-ChampaignUS6 papers
- Agency for Science, Technology and ResearchSG5 papers
- Chinese University of Hong KongHK5 papers
- University of Maryland, College ParkUS5 papers
- University of WashingtonUS5 papers
- Beihang UniversityCN4 papers
33 papers · 1 filter
HyperRouter: Towards Efficient Training and Inference of Sparse Mixture of Experts
Giang Do, Khiem Le, Quang Pham +7
By routing input tokens to only a few split experts, Sparse Mixture-of-Experts has enabled efficient training of large language models. Recent findings suggest that fixing the rout…
The AI Economist: Optimal Economic Policy Design via Two-level Deep Reinforcement Learning
Stephan Zheng, Alexander Trott, Sunil Srinivasa +2
AI and reinforcement learning (RL) have improved many areas, but are not yet widely adopted in economic policy design, mechanism design, or economics at large. At the same time, cu…
WarpDrive: Extremely Fast End-to-End Deep Multi-Agent Reinforcement Learning on a GPU
Tian Lan, Sunil Srinivasa, Huan Wang +1
Deep reinforcement learning (RL) is a powerful framework to train decision-making models in complex environments. However, RL can be slow as it requires repeated interaction with a…
: Compositional Counterfactual Contrastive Learning for Video-grounded Dialogues
Hung Le, Nancy F. Chen, Steven C. H. Hoi
Video-grounded dialogue systems aim to integrate video understanding and dialogue understanding to generate responses that are relevant to both the dialogue and video context. Most…
Exact Gap between Generalization Error and Uniform Convergence in Random Feature Models
Zitong Yang, Yu Bai, Song Mei
Recent work showed that there could be a large gap between the classical uniform convergence bound and the actual test error of zero-training-error predictors (interpolators) such…
Near-Optimal Offline Reinforcement Learning via Double Variance Reduction
Ming Yin, Yu Bai, Yu-Xiang Wang
We consider the problem of offline reinforcement learning (RL) -- a well-motivated setting of RL that aims at policy optimization using only historical data. Despite its wide appli…
Technology Readiness Levels for Machine Learning Systems
Alexander Lavin, Ciarán M. Gilligan-Lee, Alessya Visnjic +12
The development and deployment of machine learning (ML) systems can be executed easily with modern tools, but the process is typically rushed and means-to-an-end. The lack of dilig…
Communication-Aware Collaborative Learning
Avrim Blum, Shelby Heinecke, Lev Reyzin
Algorithms for noiseless collaborative PAC learning have been analyzed and optimized in recent years with respect to sample complexity. In this paper, we study collaborative PAC le…
Catastrophic Fisher Explosion: Early Phase Fisher Matrix Impacts Generalization
Stanislaw Jastrzebski, Devansh Arpit, Oliver Astrand +6
The early phase of training a deep neural network has a dramatic effect on the local curvature of the loss function. For instance, using a small learning rate does not guarantee st…
GAEA: Graph Augmentation for Equitable Access via Reinforcement Learning
Govardana Sachithanandam Ramachandran, Ivan Brugere, Lav R. Varshney +1
Disparate access to resources by different subpopulations is a prevalent issue in societal and sociotechnical networks. For example, urban infrastructure networks may enable certai…
Profile Prediction: An Alignment-Based Pre-Training Task for Protein Sequence Models
Pascal Sturmfels, Jesse Vig, Ali Madani +1
For protein sequence datasets, unlabeled data has greatly outpaced labeled data due to the high cost of wet-lab characterization. Recent deep-learning approaches to protein predict…
Online Structured Meta-learning
Huaxiu Yao, Yingbo Zhou, Mehrdad Mahdavi +3
Learning quickly is of great importance for machine intelligence deployed in online platforms. With the capability of transferring knowledge from learned tasks, meta-learning has s…
Actor-Critic Algorithm for High-dimensional Partial Differential Equations
Xiaohan Zhang
We develop a deep learning model to effectively solve high-dimensional nonlinear parabolic partial differential equations (PDE). We follow Feynman-Kac formula to reformulate PDE in…
Iterative Graph Self-Distillation
Hanlin Zhang, Shuai Lin, Weiyang Liu +4
Recently, there has been increasing interest in the challenge of how to discriminatively vectorize graphs. To address this, we propose a method called Iterative Graph Self-Distilla…
How Important is the Train-Validation Split in Meta-Learning?
Yu Bai, Minshuo Chen, Pan Zhou +5
Meta-learning aims to perform fast adaptation on a new task through learning a "prior" from multiple existing tasks. A common practice in meta-learning is to perform a train-valida…
Towards Theoretically Understanding Why SGD Generalizes Better Than ADAM in Deep Learning
Pan Zhou, Jiashi Feng, Chao Ma +3
It is not clear yet why ADAM-alike adaptive gradient algorithms suffer from worse generalization performance than SGD despite their faster training speed. This work aims to provide…
Representation Learning for Sequence Data with Deep Autoencoding Predictive Components
Junwen Bai, Weiran Wang, Yingbo Zhou +1
We propose Deep Autoencoding Predictive Components (DAPC) -- a self-supervised representation learning method for sequence data, based on the intuition that useful representations…
A Sharp Analysis of Model-based Reinforcement Learning with Self-Play
Qinghua Liu, Tiancheng Yu, Yu Bai +1
Model-based algorithms -- algorithms that explore the environment through building and utilizing an estimated model -- are widely used in reinforcement learning practice and theore…
Hybrid Stochastic-Deterministic Minibatch Proximal Gradient: Less-Than-Single-Pass Optimization with Nearly Optimal Generalization
Pan Zhou, Xiaotong Yuan
Stochastic variance-reduced gradient (SVRG) algorithms have been shown to work favorably in solving large-scale learning problems. Despite the remarkable success, the stochastic gr…
Bilevel Continual Learning
Quang Pham, Doyen Sahoo, Chenghao Liu +1
Continual learning aims to learn continuously from a stream of tasks and data in an online-learning fashion, being capable of exploiting what was learned previously to improve curr…
Near-Optimal Reinforcement Learning with Self-Play
Yu Bai, Chi Jin, Tiancheng Yu
This paper considers the problem of designing optimal algorithms for reinforcement learning in two-player zero-sum games. We focus on self-play algorithms which learn the optimal p…
Theory-Inspired Path-Regularized Differential Network Architecture Search
Pan Zhou, Caiming Xiong, Richard Socher +1
Despite its high search efficiency, differential architecture search (DARTS) often selects network architectures with dominated skip connections which lead to performance degradati…
Towards Understanding Hierarchical Learning: Benefits of Neural Representations
Minshuo Chen, Yu Bai, Jason D. Lee +4
Deep neural networks can empirically perform efficient hierarchical learning, in which the layers learn useful representations of the data. However, how they make use of the interm…
Improving GAN Training with Probability Ratio Clipping and Sample Reweighting
Yue Wu, Pan Zhou, Andrew Gordon Wilson +2
Despite success on a wide range of problems related to vision, generative adversarial networks (GANs) often suffer from inferior performance due to unstable training, especially fo…