Search Results for author:
Found 8 papers, 1 papers with code
Generalization Guarantees of Gradient Descent for Multi-Layer Neural Networks
This sheds light on sufficient or necessary conditions for under-parameterized and over-parameterized NNs trained by GD to attain the desired risk rate of $O(1/\sqrt{n})$.
Stability and Generalization for Markov Chain Stochastic Gradient Methods
To the best of our knowledge, this is the first generalization analysis of SGMs when the gradients are sampled from a Markov process.
Differentially Private Stochastic Gradient Descent with Low-Noise
In this paper, we focus on the privacy and utility (measured by excess risk bounds) performances of differentially private stochastic gradient descent (SGD) algorithms in the setting of stochastic convex optimization.
Simple Stochastic and Online Gradient Descent Algorithms for Pairwise Learning
A popular approach to handle streaming data in pairwise learning is an online gradient descent (OGD) algorithm, where one needs to pair the current instance with a buffering set of previous instances with a sufficiently large size and therefore suffers from a scalability issue.
Simple Stochastic and Online Gradient DescentAlgorithms for Pairwise Learning
A popular approach to handle streaming data in pairwise learning is an online gradient descent (OGD) algorithm, where one needs to pair the current instance with a buffering set of previous instances with a sufficiently large size and therefore suffers from a scalability issue.
Stability and Generalization for Randomized Coordinate Descent
Randomized coordinate descent (RCD) is a popular optimization algorithm with wide applications in solving various machine learning problems, which motivates a lot of theoretical analysis on its convergence behavior.
Differentially Private SGD with Non-Smooth Losses
We significantly relax these restrictive assumptions and establish privacy and generalization (utility) guarantees for private SGD algorithms using output and gradient perturbations associated with non-smooth convex losses.
Differential Privacy for Sparse Classification Learning
By the property of the post-processing holding of differential privacy, the proposed approach satisfies the $\epsilon-$differential privacy even when the original problem is unstable.
