AI Paper Atlas

Research map / Optimization / Nonconvex and smooth optimization

Lower-Level Agnostic Bilevel Optimization

Peiwen Qiu, Prashant Khanduri, Jia (Kevin) Liu

NeurIPS 2026 · Optimization › Nonconvex and smooth optimization · approach: Penalty and implicit-gradient bilevel methods · 0 citations (OpenAlex)

Read the paper

AI-extracted summary. Written by AI from the paper's full text. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Proposes a bilevel optimization method for settings where the lower-level problem is a black box (solver, simulator, adversary), so the lower-level objective cannot be evaluated, differentiated, or unrolled.

Problem

Bilevel optimization where the lower-level response comes from a black-box solver, simulator, or adversary, so standard methods that assume access to the lower-level objective (for evaluation, differentiation, or unrolling) fail.

Approach

Lower-level-agnostic bilevel optimization: the upper-level procedure only uses the output of the lower-level response, without requiring access to the lower-level objective, its gradients, or unrolled iterations. Details are not available beyond the abstract.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
use LeGo-BiO (LL-agnostic) instead of FAST-AT / FAST-AT-GAadversarial training PreActResNet-18 · CIFAR-10standard and robust accuracy: standard 73.34 -> 77.18; robust 32.56 -> 39.08 (vs FAST-AT)Improved
use LeGo-BiO (no LL objective access) instead of FAST-BATadversarial training · CIFAR-10standard / robust accuracy: standard 76.04 -> 77.18; robust 39.84 -> 39.08Mixed
use LeGo-BiO instead of zeroth-order ZDSBAdeep hyper-representation on MNIST LeNet · MNISTtraining lossImproved
reduce LL approximation error of the response oracle (ablation)LeGo-BiO · MNIST deep hyper-representationiterations to reach same training lossImproved
vary LL approximation error level (ablation)LeGo-BiO · MNIST deep hyper-representationfinal training lossNo clear effect
swap LL solver among SGD, Adam and SciPy (ablation)LeGo-BiO · MNIST deep hyper-representationtraining lossMixed
use LeGo-BiO instead of SOBA/MA-SOBAdata weighting for Llama-3.2-1B-Instruct on HH-RLHF · HH-RLHFconvergence speedImproved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy