Optimization
A Unified Framework for Rank-based Loss Minimization
The empirical risk function is the cornerstone of machine learning.
Bilevel Coreset Selection in Continual Learning: A New Formulation and Algorithm
However, the typical bilevel formulation for coreset selection explicitly performs optimization over discrete decision variables with greedy search, which is computationally expensive.
BiSLS/SPS: Auto-tune Step Sizes for Stable Bi-level Optimization Chen Fan
This unified envelope strategy allows for the extension of the algorithms and their convergence guarantees to BO settings.
T2T: From Distribution Learning in Training to Gradient Search in Testing for Combinatorial Optimization
Figure 2: Diffusion modeling for CO solving where the model learns how to gradually denoise from the random noise to predict each step's
Learning to Search Feasible and Infeasible Regions of Routing Problems with Flexible Neural k-Opt
Notably, we offer fresh perspectives on how neural solvers can handle VRP constraints.