Nature

Accelerated ensemble optimization using momentum methods

We study the effect of using momentum (accumulation of earlier gradients) with the ensemble optimization method (EnOpt) for production optimization. Since its introduction to this field by Chen et al.
Nature

Convergence analysis and application for high-order neural networks based on gradient descent learning algorithm via smooth regularization

Higher order networks (HONs) extend the traditional pairwise interactions between nodes to higher order interactions involving three or more nodes. This allows for the modeling of more complex ...
Harvard Business School

Descent-to-Delete: Gradient-Based Methods for Machine Unlearning

Neel, Seth, Aaron Leon Roth, and Saeed Sharifi-Malvajerdi. "Descent-to-Delete: Gradient-Based Methods for Machine Unlearning." Paper presented at the 32nd Algorithmic Learning Theory Conference, March ...