W Yao, C Yu, S Zeng, J Zhang - arXiv preprint arXiv:2401.16164, 2024 - arxiv.org
This paper presents a new approach and algorithm for solving a class of constrained Bi- Level Optimization (BLO) problems in which the lower-level problem involves constraints …
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 …
We study the problem of efficiently computing the derivative of the fixed-point of a parametric non-differentiable contraction map. This problem has wide applications in machine learning …
Two-level stochastic optimization formulations have become instrumental in a number of machine learning contexts such as continual learning, neural architecture search …
I Tsaknakis, P Khanduri, M Hong - ICASSP 2023-2023 IEEE …, 2023 - ieeexplore.ieee.org
In this work, we propose algorithms for solving a class of Bilevel Optimization (BLO) problems, with applications in areas such as signal processing, networking and machine …
We develop new algorithms for Riemannian bilevel optimization. We focus in particular on batch and stochastic gradient-based methods, with the explicit goal of avoiding second …
Algorithms for bilevel optimization often encounter Hessian computations, which are prohibitive in high dimensions. While recent works offer first-order methods for …