Search Results for author:
Found 10 papers, 3 papers with code
S$^{2}$FT: Efficient, Scalable and Generalizable LLM Fine-tuning by Structured Sparsity
Utilizing this key insight, we propose a family of Structured Sparse Fine-Tuning (S$^{2}$FT) methods for LLMs, which concurrently achieve state-of-the-art fine-tuning performance, training efficiency, and inference scalability.
NEAT: Nonlinear Parameter-efficient Adaptation of Pre-trained Models
The nonlinear approximation directly models the cumulative updates, effectively capturing complex and non-linear structures in the weight updates.
Synthetic Oversampling: Theory and A Practical Approach Using LLMs to Address Data Imbalance
Imbalanced data and spurious correlations are common challenges in machine learning and data science.
Differentially Private Federated Learning: Servers Trustworthiness, Estimation, and Statistical Inference
Differentially private federated learning is crucial for maintaining privacy in distributed environments.
Contrastive Learning on Multimodal Analysis of Electronic Health Records
To accommodate the statistical analysis of multimodal EHR data, in this paper, we propose a novel multimodal feature embedding generative model and design a multimodal contrastive loss to obtain the multimodal EHR feature representation.
Safeguarding Data in Multimodal AI: A Differentially Private Approach to CLIP Training
The surge in multimodal AI's success has sparked concerns over data privacy in vision-and-language tasks.
Understanding Multimodal Contrastive Learning and Incorporating Unpaired Data
We show that the algorithm can detect the ground-truth pairs and improve performance by fully exploiting unpaired datasets.
The Power of Contrast for Feature Learning: A Theoretical Analysis
Contrastive learning has achieved state-of-the-art performance in various self-supervised learning tasks and even outperforms its supervised counterpart.
Asymptotic Risk of Overparameterized Likelihood Models: Double Descent Theory for Deep Neural Networks
We investigate the asymptotic risk of a general class of overparameterized likelihood models, including deep models.
Adaptive Approximation and Generalization of Deep Neural Network with Intrinsic Dimensionality
In this study, we prove that an intrinsic low dimensionality of covariates is the main factor that determines the performance of deep neural networks (DNNs).
