Search Results for author:
Found 9 papers, 1 papers with code
Meta-Shop: Improving Item Advertisement For Small Businesses
Training samples in RS can be highly biased toward popular businesses with sufficient sales and can decrease advertising performance for small businesses.
An Efficient Algorithm for Deep Stochastic Contextual Bandits
In this work, we formulate the SCB that uses a DNN reward function as a non-convex stochastic optimization problem, and design a stage-wise stochastic gradient descent algorithm to optimize the problem and determine the action policy.
Escaping Saddle Points with Stochastically Controlled Stochastic Gradient Methods
Stochastically controlled stochastic gradient (SCSG) methods have been proved to converge efficiently to first-order stationary points which, however, can be saddle points in nonconvex optimization.
Federated Nonconvex Sparse Learning
Nonconvex sparse learning plays an essential role in many areas, such as signal processing and deep network compression.
Effective Proximal Methods for Non-convex Non-smooth Regularized Learning
Sparse learning is a very important tool for mining useful information and patterns from high dimensional data.
Effective Federated Adaptive Gradient Methods with Non-IID Decentralized Data
Federated learning allows loads of edge computing devices to collaboratively learn a global model without data sharing.
Towards Plausible Differentially Private ADMM Based Distributed Machine Learning
In PP-ADMM, each agent approximately solves a perturbed optimization problem that is formulated from its local private data in an iteration, and then perturbs the approximate solution with Gaussian noise to provide the DP guarantee.
Calibrating the Adaptive Learning Rate to Improve Convergence of ADAM
Theoretically, we provide a new way to analyze the convergence of AGMs and prove that the convergence rate of \textsc{Adam} also depends on its hyper-parameter $\epsilon$, which has been overlooked previously.
A Sparse Interactive Model for Matrix Completion with Side Information
We prove that when the side features can span the latent feature space of the matrix to be recovered, the number of observed entries needed for an exact recovery is $O(\log N)$ where $N$ is the size of the matrix.
