28 citations · 70 across the 16 of their papers we have counts for
16 papers
Exploring More to Solve More: Boosting Diversity in Text Diffusion Models via Entropy-Based Guidance
Jingwei Zhang, Haoyu Lei, Zijin Feng +2
Although diffusion models have revolutionized continuous domains like image synthesis through high quality generations and controllable guidance mechanisms, bringing this controlla…
When Kernels Multiply, Clusters Unify: Fusing Embeddings with the Kronecker Product
Youqi Wu, Jingwei Zhang, Farzan Farnia
State-of-the-art embeddings often capture distinct yet complementary discriminative features: For instance, one image embedding model may excel at distinguishing fine-grained textu…
A Super-pixel-based Approach to the Stable Interpretation of Neural Networks
Shizhan Gong, Jingwei Zhang, Qi Dou +1
Saliency maps are widely used in the computer vision community for interpreting neural network classifiers. However, due to the randomness of training samples and optimization algo…
Towards a Scalable Reference-Free Evaluation of Generative Models
Azim Ospanov, Jingwei Zhang, Mohammad Jalali +3
While standard evaluation scores for generative models are mostly reference-based, a reference-dependent assessment of generative models could be generally difficult due to the una…
MoreauPruner: Robust Pruning of Large Language Models against Weight Perturbations
Zixiao Wang, Jingwei Zhang, Wenqian Zhao +2
Few-shot gradient methods have been extensively utilized in existing model pruning methods, where the model weights are regarded as static values and the effects of potential weigh…
Sparse Domain Transfer via Elastic Net Regularization
Jingwei Zhang, Farzan Farnia
Transportation of samples across different domains is a central task in several machine learning problems. A sensible requirement for domain transfer tasks in computer vision and l…
Unveiling Differences in Generative Models: A Scalable Differential Clustering Approach
Jingwei Zhang, Mohammad Jalali, Cheuk Ting Li +1
A fine-grained comparison of generative models requires the identification of sample types generated differently by each of the involved models. While quantitative scores have been…
An Interpretable Evaluation of Entropy-based Novelty of Generative Models
Jingwei Zhang, Cheuk Ting Li, Farzan Farnia
The massive developments of generative model frameworks require principled methods for the evaluation of a model's novelty compared to a reference dataset. While the literature has…
DiffFlow: A Unified SDE Framework for Score-Based Diffusion Models and Generative Adversarial Networks
Jingwei Zhang, Han Shi, Jincheng Yu +2
Generative models can be categorized into two types: explicit generative models that define explicit density forms and allow exact likelihood inference, such as score-based diffusi…
MoreauGrad: Sparse and Robust Interpretation of Neural Networks via Moreau Envelope
Jingwei Zhang, Farzan Farnia
Explaining the predictions of deep neural nets has been a topic of great interest in the computer vision literature. While several gradient-based interpretation schemes have been p…
Mean-Field Analysis of Two-Layer Neural Networks: Global Optimality with Linear Convergence Rates
Jingwei Zhang, Xunpeng Huang, Jincheng Yu
We consider optimizing two-layer neural networks in the mean-field regime where the learning dynamics of network weights can be approximated by the evolution in the space of probab…
Generalization Bounds for Convolutional Neural Networks
Shan Lin, Jingwei Zhang
Convolutional neural networks (CNNs) have achieved breakthrough performances in a wide range of applications including image classification, semantic segmentation, and object detec…
An Optimal Transport View on Generalization
Jingwei Zhang, Tongliang Liu, Dacheng Tao
We derive upper bounds on the generalization error of learning algorithms based on their \emph{algorithmic transport cost}: the expected Wasserstein distance between the output hyp…
Theoretical Analysis of Adversarial Learning: A Minimax Approach
Zhuozhuo Tu, Jingwei Zhang, Dacheng Tao
Here we propose a general theoretical method for analyzing the risk bound in the presence of adversaries. Specifically, we try to fit the adversarial learning problem into the mini…
An Information-Theoretic View for Deep Learning
Jingwei Zhang, Tongliang Liu, Dacheng Tao
Deep learning has transformed computer vision, natural language processing, and speech recognition\cite{badrinarayanan2017segnet, dong2016image, ren2017faster, ji20133d}. However,…
On the Rates of Convergence from Surrogate Risk Minimizers to the Bayes Optimal Classifier
Jingwei Zhang, Tongliang Liu, Dacheng Tao
We study the rates of convergence from empirical surrogate risk minimizers to the Bayes optimal classifier. Specifically, we introduce the notion of \emph{consistency intensity} to…