REVIEW 4 cited by
Moreau Envelope Based Difference-of-weakly-Convex Reformulation and Algorithm for Bilevel Programs
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
Moreau Envelope Based Difference-of-weakly-Convex Reformulation and Algorithm for Bilevel Programs
read the original abstract
Bilevel programming has emerged as a valuable tool for hyperparameter selection, a central concern in machine learning. In a recent study by Ye et al. (2023), a value function-based difference of convex algorithm was introduced to address bilevel programs. This approach proves particularly powerful when dealing with scenarios where the lower-level problem exhibits convexity in both the upper-level and lower-level variables. Examples of such scenarios include support vector machines and $\ell_1$ and $\ell_2$ regularized regression. In this paper, we significantly expand the range of applications, now requiring convexity only in the lower-level variables of the lower-level program. We present an innovative single-level difference of weakly convex reformulation based on the Moreau envelope of the lower-level problem. We further develop a sequentially convergent Inexact Proximal Difference of Weakly Convex Algorithm (iP-DwCA). To evaluate the effectiveness of the proposed iP-DwCA, we conduct numerical experiments focused on tuning hyperparameters for kernel support vector machines on simulated data.
Forward citations
Cited by 4 Pith papers
-
Select-then-differentiate: Solving Bilevel Optimization with Manifold Lower-level Solution Sets
Optimistic bilevel optimization with manifold lower-level minimizers is differentiable if the optimistic selection is unique, yielding a pseudoinverse hyper-gradient and a convergent HG-MS algorithm whose rate depends...
-
Hypergradient-based Bilevel Reinforcement Learning with Improved Sample Complexity
A bilevel RL algorithm using Boltzmann-policy optimality achieves Õ(ε⁻²) sample complexity for first-order stationarity, removing the outer-level PL condition but relying on a non-realizability error bound that is not proven.
-
A Single-Loop Bilevel Deep Learning Method for Optimal Control of Obstacle Problems
Optimal control of obstacle problems is solved mesh-free by training constraint-embedding neural networks with S2-FOBA, a single-loop stochastic bilevel algorithm whose Moreau-penalized gradient converges sublinearly.
-
Alternating Gradient-Type Algorithm for Bilevel Optimization with Inexact Lower-Level Solutions via Moreau Envelope-based Reformulation
AGILS is an alternating gradient algorithm for bilevel optimization that uses Moreau envelope reformulation to handle inexact lower-level solves, with convergence to stationary points proven under stated assumptions.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.