Bi-EZP: LLM-Guided Bilevel Program Evolution for Ensemble Zero-Cost Proxy Discovery

• URL: http://arxiv.org/abs/2608.21927v1
• Date: Sat, 22 Aug 2026 11:34:35 GMT
• Title: Bi-EZP: LLM-Guided Bilevel Program Evolution for Ensemble Zero-Cost Proxy Discovery
• Abstract summary: Bi-EZP is a bilevel framework that separates program discovery from numerical calibration.<n>Results show that separating program discovery from numerical calibration provides an effective approach to automated ensemble zero-cost proxy construction.
• Score: 2.751603258501323
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Zero-cost proxies enable neural architecture search (NAS) to rank candidate networks from statistics computed at initialization, avoiding repeated training. However, different proxies capture different properties and often produce inconsistent rankings across search spaces. Ensemble proxies can combine complementary signals, but automated discovery must optimize both discrete aggregation structures and their continuous coefficients, making structural quality difficult to separate from parameter calibration. We propose Bi-EZP, a bilevel framework that decouples these decisions. At the upper level, a large language model generates executable aggregation programs over four complementary base proxies with program-specific parameter bounds. At the lower level, covariance matrix adaptation evolution strategy (CMA-ES) optimizes the continuous parameters of each fixed program on an inner training split. The calibrated programs are then evaluated using Kendall's rank correlation on a disjoint validation split, enabling evolutionary selection to favor structures that generalize beyond their calibration data. Experiments on NATS-Bench and Network Design Spaces evaluate ranking performance across heterogeneous search spaces, and DARTS experiments assess downstream architecture search. Results show that separating program discovery from numerical calibration provides an effective approach to automated ensemble zero-cost proxy construction. The source code is available at: https://anonymous.4open.science/r/Bi-EZP-318D

Related papers

• Localized Anomaly Detection via Differentiable D-vine Copulas [3.071933369858584]
  We propose a novel estimation framework that combines gradient-based maximum likelihood estimation, enabled by our fully differentiable implementation, with a beam-search strategy.<n>Building on the fitted D-vine, we introduce a localized anomaly detection framework that exploits the hierarchical decomposition to produce both global anomaly scores and edge-level explanations.<n>We evaluate the proposed framework on both benchmark and real-world datasets, demonstrating its effectiveness for interpretable anomaly detection with uncertainty.
  arXiv  Detail & Related papers  (2026-07-27T19:29:26Z)
• Convergence Theory for Iterative LLM-Based Neural Architecture Search: A Parametric Cross-Entropy Framework with Closed-Form Proxy Reliability [48.83701310501069]
  Large language models (LLMs) are increasingly used as generators in iterative neural architecture search (NAS)<n>We model iterative LLM-NAS as a parametric Cross-Entropy (CE) method over executable programs.<n>We prove six results: (1) iterative LLM fine-tuning on elite architectures is equivalent to the CE update restricted to the LLM family; (2) expected architecture quality is monotonically non-decreasing across cycles; and (3) elite-set probability converges to a fixed point at a geometric rate.
  arXiv  Detail & Related papers  (2026-05-28T15:45:19Z)
• AgenticRS-EnsNAS: Ensemble-Decoupled Self-Evolving Architecture Search [10.111487060179252]
  This work introduces Ensemble-Decoupled Architecture Search.<n>It predicts system-level performance from single-learner evaluation.<n>It reduces per-candidate search cost from O(M) to O(1) while maintaining O(M) deployment cost only for validated winners.
  arXiv  Detail & Related papers  (2026-03-20T14:57:15Z)
• Accelerating Benchmarking of Functional Connectivity Modeling via Structure-aware Core-set Selection [8.347306013377041]
  We formalize Contrastive Learning for Core-set Selection (SCLCS) as a ranking- subset selection problem.<n>SCLCS identifies stable samples via a top-k ranking, Structural Perturbation Score, and density-balanced sampling strategy.<n>On the large-scale REST-meta-MDD dataset, SCLCS preserves the ground-truth model ranking with just 10% of the data, outperforming state-of-the-art (SOTA) core-set selection methods by up to 23.2% in ranking consistency (nDCG@k)
  arXiv  Detail & Related papers  (2026-02-05T13:50:39Z)
• Towards Zero-Shot Point Cloud Registration Across Diverse Scales, Scenes, and Sensor Setups [41.033896572767496]
  We present BUFFER-X, a training-free registration framework that achieves zero-shot generalization.<n>Our approach employs hierarchical multi-scale matching to extract correspondences across local, middle, and global receptive fields.<n>For efficiency-critical applications, we introduce BUFFER-X-Lite, which reduces total time by 43%.
  arXiv  Detail & Related papers  (2026-01-06T06:51:24Z)
• Learning Discrete Bayesian Networks with Hierarchical Dirichlet Shrinkage [52.914168158222765]
  We detail a comprehensive Bayesian framework for learning DBNs.<n>We give a novel Markov chain Monte Carlo (MCMC) algorithm utilizing parallel Langevin proposals to generate exact posterior samples.<n>We apply our methodology to uncover prognostic network structure from primary breast cancer samples.
  arXiv  Detail & Related papers  (2025-09-16T17:24:35Z)
• Adaptive and Robust DBSCAN with Multi-agent Reinforcement Learning [53.527506374566485]
  We propose a novel Adaptive and Robust DBSCAN with Multi-agent Reinforcement Learning cluster framework, namely AR-DBSCAN.<n>We show that AR-DBSCAN not only improves clustering accuracy by up to 144.1% and 175.3% in the NMI and ARI metrics, respectively, but also is capable of robustly finding dominant parameters.
  arXiv  Detail & Related papers  (2025-05-07T11:37:23Z)
• MOKD: Cross-domain Finetuning for Few-shot Classification via Maximizing Optimized Kernel Dependence [97.93517982908007]
  In cross-domain few-shot classification, NCC aims to learn representations to construct a metric space where few-shot classification can be performed. In this paper, we find that there exist high similarities between NCC-learned representations of two samples from different classes. We propose a bi-level optimization framework, emphmaximizing optimized kernel dependence (MOKD) to learn a set of class-specific representations that match the cluster structures indicated by labeled data.
  arXiv  Detail & Related papers  (2024-05-29T05:59:52Z)
• SC^2-PCR: A Second Order Spatial Compatibility for Efficient and Robust Point Cloud Registration [32.87420625579577]
  We propose a second order spatial compatibility (SC2) measure to compute the similarity between correspondences. Based on this measure, our registration pipeline employs a global spectral technique to find some reliable seeds from the initial correspondences. Our method can guarantee to find a certain number of outlier-free consensus sets using fewer samplings.
  arXiv  Detail & Related papers  (2022-03-28T02:41:28Z)
• Optimal Clustering with Bandit Feedback [57.672609011609886]
  This paper considers the problem of online clustering with bandit feedback. It includes a novel stopping rule for sequential testing that circumvents the need to solve any NP-hard weighted clustering problem as its subroutines. We show through extensive simulations on synthetic and real-world datasets that BOC's performance matches the lower boundally, and significantly outperforms a non-adaptive baseline algorithm.
  arXiv  Detail & Related papers  (2022-02-09T06:05:05Z)
• Neural Ensemble Search for Uncertainty Estimation and Dataset Shift [67.57720300323928]
  Ensembles of neural networks achieve superior performance compared to stand-alone networks in terms of accuracy, uncertainty calibration and robustness to dataset shift. We propose two methods for automatically constructing ensembles with emphvarying architectures. We show that the resulting ensembles outperform deep ensembles not only in terms of accuracy but also uncertainty calibration and robustness to dataset shift.
  arXiv  Detail & Related papers  (2020-06-15T17:38:15Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.