52 citations · 212 across the 22 of their papers we have counts for
22 papers
Efficient Transformer-based 3D Object Detection with Dynamic Token Halting
Mao Ye, Gregory P. Meyer, Yuning Chai +1
Balancing efficiency and accuracy is a long-standing problem for deploying deep learning models. The trade-off is even more important for real-time safety-critical systems like aut…
First Hitting Diffusion Models for Generating Manifold, Graph and Categorical Data
Mao Ye, Lemeng Wu, Qiang Liu
We propose a family of First Hitting Diffusion Models (FHDM), deep generative models that generate data with a diffusion process that terminates at a random first hitting time. Thi…
BOME! Bilevel Optimization Made Easy: A Simple First-Order Approach
Mao Ye, Bo Liu, Stephen Wright +2
Bilevel optimization (BO) is useful for solving a variety of important machine learning problems including but not limited to hyperparameter optimization, meta-learning, continual…
Future Gradient Descent for Adapting the Temporal Shifting Data Distribution in Online Recommendation Systems
Mao Ye, Ruichen Jiang, Haoxiang Wang +6
One of the key challenges of learning an online recommendation model is the temporal domain shift, which causes the mismatch between the training and testing data distribution and…
Diffusion-based Molecule Generation with Informative Prior Bridges
Lemeng Wu, Chengyue Gong, Xingchao Liu +2
AI-based molecule generation provides a promising approach to a large area of biomedical sciences and engineering, such as antibody design, hydrolase engineering, or vaccine develo…
Bit Allocation using Optimization
Tongda Xu, Han Gao, Chenjian Gao +10
In this paper, we consider the problem of bit allocation in Neural Video Compression (NVC). First, we reveal a fundamental relationship between bit allocation in NVC and Semi-Amort…
Let us Build Bridges: Understanding and Extending Diffusion Generative Models
Xingchao Liu, Lemeng Wu, Mao Ye +1
Diffusion-based generative models have achieved promising results recently, but raise an array of open questions in terms of conceptual understanding, theoretical analysis, algorit…
Centroid Approximation for Bootstrap: Improving Particle Quality at Inference
Mao Ye, Qiang Liu
Bootstrap is a principled and powerful frequentist statistical tool for uncertainty quantification. Unfortunately, standard bootstrap methods are computationally intensive due to t…
Pareto Navigation Gradient Descent: a First-Order Algorithm for Optimization in Pareto Set
Mao Ye, Qiang Liu
Many modern machine learning applications, such as multi-task learning, require finding optimal model parameters to trade-off multiple objective functions that may conflict with ea…
VCNet and Functional Targeted Regularization For Learning Causal Effects of Continuous Treatments
Lizhen Nie, Mao Ye, Qiang Liu +1
Motivated by the rising abundance of observational data with continuous treatments, we investigate the problem of estimating the average dose-response curve (ADRF). Available param…
Greedy Optimization Provably Wins the Lottery: Logarithmic Number of Winning Tickets is Enough
Mao Ye, Lemeng Wu, Qiang Liu
Despite the great success of deep learning, recent works show that large deep neural networks are often highly redundant and can be significantly reduced in size. However, the theo…
Adaptive Dense-to-Sparse Paradigm for Pruning Online Recommendation System with Non-Stationary Data
Mao Ye, Dhruv Choudhary, Jiecao Yu +6
Large scale deep learning provides a tremendous opportunity to improve the quality of content recommendation systems by employing both wider and deeper models, but this comes at gr…
Go Wide, Then Narrow: Efficient Training of Deep Thin Networks
Denny Zhou, Mao Ye, Chen Chen +6
For deploying a deep learning model into production, it needs to be both accurate and compact to meet the latency and memory constraints. This usually results in a network that is…
SAFER: A Structure-free Approach for Certified Robustness to Adversarial Word Substitutions
Mao Ye, Chengyue Gong, Qiang Liu
State-of-the-art NLP models can often be fooled by human-unaware transformations such as synonymous word substitution. For security reasons, it is of critical importance to develop…
Joint COCO and Mapillary Workshop at ICCV 2019 Keypoint Detection Challenge Track Technical Report: Distribution-Aware Coordinate Representation for Human Pose Estimation
Hanbin Dai, Liangbo Zhou, Feng Zhang +4
In this paper, we focus on the coordinate representation in human pose estimation. While being the standard choice, heatmap based representation has not been systematically investi…
Steepest Descent Neural Architecture Optimization: Escaping Local Optimum with Signed Neural Splitting
Lemeng Wu, Mao Ye, Qi Lei +2
Developing efficient and principled neural architecture optimization methods is a critical challenge of modern deep learning. Recently, Liu et al.[19] proposed a splitting steepest…
Good Subnetworks Provably Exist: Pruning via Greedy Forward Selection
Mao Ye, Chengyue Gong, Lizhen Nie +3
Recent empirical works show that large deep neural networks are often highly redundant and one can find much smaller subnetworks without a significant drop of accuracy. However, mo…
MaxUp: A Simple Way to Improve Generalization of Neural Network Training
Chengyue Gong, Tongzheng Ren, Mao Ye +1
We propose \emph{MaxUp}, an embarrassingly simple, highly effective technique for improving the generalization performance of machine learning models, especially deep neural networ…
Black-Box Certification with Randomized Smoothing: A Functional Optimization Based Framework
Dinghuai Zhang, Mao Ye, Chengyue Gong +2
Randomized classifiers have been shown to provide a promising approach for achieving certified robustness against adversarial attacks in deep learning. However, most existing metho…
Stein Self-Repulsive Dynamics: Benefits From Past Samples
Mao Ye, Tongzheng Ren, Qiang Liu
We propose a new Stein self-repulsive dynamics for obtaining diversified samples from intractable un-normalized distributions. Our idea is to introduce Stein variational gradient a…
Post-training Quantization with Multiple Points: Mixed Precision without Mixed Precision
Xingchao Liu, Mao Ye, Dengyong Zhou +1
We consider the post-training quantization problem, which discretizes the weights of pre-trained deep neural networks without re-training the model. We propose multipoint quantizat…
Stein Neural Sampler
Tianyang Hu, Zixiang Chen, Hanxi Sun +3
We propose two novel samplers to generate high-quality samples from a given (un-normalized) probability density. Motivated by the success of generative adversarial networks, we con…