Search Results for author:
Found 9 papers, 3 papers with code
Inference and Interference: The Role of Clipping, Pruning and Loss Landscapes in Differentially Private Stochastic Gradient Descent
Differentially private stochastic gradient descent (DP-SGD) is known to have poorer training and test performance on large neural networks, compared to ordinary stochastic gradient descent (SGD).
Accelerated Shapley Value Approximation for Data Evaluation
In pre-trained networks the approach is found to bring more efficiency in terms of accurate evaluation using small subsets.
Towards Understanding the Interplay of Generative Artificial Intelligence and the Internet
Our results show that the quality and diversity of the generated images can degrade over time suggesting that incorporating AI-created data can have undesired effects on future versions of generative models.
Combining Generative Artificial Intelligence (AI) and the Internet: Heading towards Evolution or Degradation?
Therefore, future versions of generative AI tools will be trained with Internet data that is a mix of original and AI-generated data.
Differentially Private Shapley Values for Data Evaluation
The Shapley value has been proposed as a solution to many applications in machine learning, including for equitable valuation of data.
Continual and Sliding Window Release for Private Empirical Risk Minimization
One version of the algorithm uses the entire data history to improve the model for the recent window.
The Shapley Value in Machine Learning
Over the last few years, the Shapley value, a solution concept from cooperative game theory, has found numerous applications in machine learning.
On the Importance of Difficulty Calibration in Membership Inference Attacks
The vulnerability of machine learning models to membership inference attacks has received much attention in recent years.
Stability Enhanced Privacy and Applications in Private Stochastic Gradient Descent
Private machine learning involves addition of noise while training, resulting in lower accuracy.
