490 citations · 1.5k across the 111 of their papers we have counts for
19 papers · 1 filter
Adaptive Incentive Design with Multi-Agent Meta-Gradient Reinforcement Learning
Jiachen Yang, Ethan Wang, Rakshit Trivedi +2
Critical sectors of human society are progressing toward the adoption of powerful artificial intelligence (AI) agents, which are trained individually on behalf of self-interested p…
Learning Generalizable Vision-Tactile Robotic Grasping Strategy for Deformable Objects via Transformer
Yunhai Han, Kelin Yu, Rahul Batra +6
Reliable robotic grasping, especially with deformable objects such as fruits, remains a challenging task due to underactuated contact interactions with a gripper, unknown object dy…
Frequency-aware SGD for Efficient Embedding Learning with Provable Benefits
Yan Li, Dhruv Choudhary, Xiaohan Wei +4
Embedding learning has found widespread applications in recommendation systems and natural language modeling, among other domains. To learn quality embeddings efficiently, adaptive…
Taming Sparsely Activated Transformer with Stochastic Experts
Simiao Zuo, Xiaodong Liu, Jian Jiao +5
Sparsely activated models (SAMs), such as Mixture-of-Experts (MoE), can easily scale to have outrageously large amounts of parameters without significant increase in computational…
Large Learning Rate Tames Homogeneity: Convergence and Balancing Effect
Yuqing Wang, Minshuo Chen, Tuo Zhao +1
Recent empirical advances show that training deep models with large learning rate often improves generalization performance. However, theoretical justifications on the benefits of…
Besov Function Approximation and Binary Classification on Low-Dimensional Manifolds Using Convolutional Residual Networks
Hao Liu, Minshuo Chen, Tuo Zhao +1
Most of existing statistical theories on deep neural networks have sample complexities cursed by the data dimension and therefore cannot well explain the empirical success of deep…
Adversarially Regularized Policy Learning Guided by Trajectory Optimization
Zhigen Zhao, Simiao Zuo, Tuo Zhao +1
Recent advancement in combining trajectory optimization with function approximation (especially neural networks) shows promise in learning complex control policies for diverse task…
Self-Training with Differentiable Teacher
Simiao Zuo, Yue Yu, Chen Liang +5
Self-training achieves enormous success in various semi-supervised and weakly-supervised learning tasks. The method can be interpreted as a teacher-student framework, where the tea…
ARCH: Efficient Adversarial Regularized Training with Caching
Simiao Zuo, Chen Liang, Haoming Jiang +5
Adversarial regularization can improve model generalization in many natural language processing tasks. However, conventional approaches are computationally expensive since they nee…
Implicit Regularization of Bregman Proximal Point Algorithm and Mirror Descent on Separable Data
Yan Li, Caleb Ju, Ethan X. Fang +1
Bregman proximal point algorithm (BPPA) has witnessed emerging machine learning applications, yet its theoretical understanding has been largely unexplored. We study the computatio…
Named Entity Recognition with Small Strongly Labeled and Large Weakly Labeled Data
Haoming Jiang, Danqing Zhang, Tianyu Cao +2
Weak supervision has shown promising results in many natural language processing tasks, such as Named Entity Recognition (NER). Existing work mainly focuses on learning deep NER mo…
COUnty aggRegation mixup AuGmEntation (COURAGE) COVID-19 Prediction
Siawpeng Er, Shihao Yang, Tuo Zhao
The global spread of COVID-19, the disease caused by the novel coronavirus SARS-CoV-2, has cast a significant threat to mankind. As the COVID-19 situation continues to evolve, pred…
Super Tickets in Pre-Trained Language Models: From Model Compression to Improving Generalization
Chen Liang, Simiao Zuo, Minshuo Chen +5
The Lottery Ticket Hypothesis suggests that an over-parametrized network consists of ``lottery tickets'', and training a certain collection of them (i.e., a subnetwork) can match t…
Permutation Invariant Policy Optimization for Mean-Field Multi-Agent Reinforcement Learning: A Principled Approach
Yan Li, Lingxiao Wang, Jiachen Yang +4
Multi-agent reinforcement learning (MARL) becomes more challenging in the presence of more agents, as the capacity of the joint state and action spaces grows exponentially in the n…
Adversarial Regularization as Stackelberg Game: An Unrolled Optimization Approach
Simiao Zuo, Chen Liang, Haoming Jiang +5
Adversarial regularization has been shown to improve the generalization performance of deep learning models in various natural language processing tasks. Existing works usually for…
Token-wise Curriculum Learning for Neural Machine Translation
Chen Liang, Haoming Jiang, Xiaodong Liu +4
Existing curriculum learning approaches to Neural Machine Translation (NMT) require sampling sufficient amounts of "easy" samples from training data at the early training stage. Th…
Reinforcement Learning for Adaptive Mesh Refinement
Jiachen Yang, Tarik Dzanic, Brenden Petersen +9
Large-scale finite element simulations of complex physical systems governed by partial differential equations (PDE) crucially depend on adaptive mesh refinement (AMR) to allocate c…
Noisy Gradient Descent Converges to Flat Minima for Nonconvex Matrix Factorization
Tianyi Liu, Yan Li, Song Wei +2
Numerous empirical evidences have corroborated the importance of noise in nonconvex optimization problems. The theory behind such empirical observations, however, is still largely…
Towards Automatic Evaluation of Dialog Systems: A Model-Free Off-Policy Evaluation Approach
Haoming Jiang, Bo Dai, Mengjiao Yang +2
Reliable automatic evaluation of dialogue systems under an interactive environment has long been overdue. An ideal environment for evaluating dialog systems, also known as the Turi…