2 code implementations • 17 Jan 2024 • Charles Dickens, Changyu Gao, Connor Pryor, Stephen Wright, Lise Getoor
We address a key challenge for neuro-symbolic (NeSy) systems by leveraging convex and bilevel optimization techniques to develop a general gradient-based framework for end-to-end neural and symbolic parameter learning.
no code implementations • 9 Feb 2023 • Changyu Gao, Stephen J. Wright
We develop simple differentially private optimization algorithms that move along directions of (expected) descent to find an approximate second-order solution for nonconvex ERM.