Feasible-First Exploration for Constrained ML Deployment Optimization in Crash-Prone Hierarchical Search Spaces

• URL: http://arxiv.org/abs/2604.25073v1
• Date: Mon, 27 Apr 2026 23:58:24 GMT
• Title: Feasible-First Exploration for Constrained ML Deployment Optimization in Crash-Prone Hierarchical Search Spaces
• Abstract summary: This paper studies whether optimization should be into an explicit exploration stage followed by model-guided exploitation.<n>We propose Thermal Budget Annealing (TBA), a feasible-first exploration procedure that maps valid and feasible regions.<n>We also introduce DeployBench, a benchmark suite for deployment optimization with hierarchical structure, hidden crash zones, hard constraints, and unequal evaluation costs.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Deploying machine learning models under production constraints requires joint optimization over model family, quantization scheme, runtime backend, and serving configuration. This induces a hierarchical mixed-variable search space in which many configurations are invalid: evaluations may crash, exceed memory limits, or violate latency constraints. Standard black-box optimizers such as Tree-structured Parzen Estimators (TPE) and constrained Bayesian optimization are effective when valid configurations are common, but they can spend a large fraction of a small evaluation budget on invalid or uninformative trials in hostile deployment spaces. This paper studies that regime and asks whether optimization should be decomposed into an explicit exploration stage followed by model-guided exploitation. We propose Thermal Budget Annealing (TBA), a feasible-first exploration procedure that maps valid and feasible regions before warm-starting TPE. The method includes two robustness mechanisms for hostile hardware: trial timeouts that abort clearly infeasible evaluations early, and subspace blacklisting that temporarily suppresses categorical subspaces after repeated failures. We also introduce DeployBench, a benchmark suite for deployment optimization with hierarchical structure, hidden crash zones, hard constraints, and unequal evaluation costs. On synthetic benchmarks and real GPU deployment with five pre-trained vision models across five GPU targets (NVIDIA H100, A100, RTX 5080, L4, and T4), the proposed hybrid improves model-family discovery under tight constraints while reducing wasted budget relative to cold-start TPE.

Related papers

• Can Bayesian Optimization Efficiently Find a Strong Single Expert in Neural Thickets? [44.39621309549252]
  We show that a surrogate-guided search can substantially reduce the evaluation cost of gradient-free post-training.<n>Our method requires no backpropagation and uses a Gaussian process surrogate to guide candidate evaluations efficiently.<n>These results show that surrogate-guided search can substantially reduce the evaluation cost of gradient-free post-training while producing stronger deployable single experts.
  arXiv  Detail & Related papers  (2026-08-11T12:41:49Z)
• Multi-Objective Structured Pruning of LLMs for Latency and Model Size Optimization [2.3012967702331313]
  Large Language Models (LLMs) have achieved widespread adoption because of their strong reasoning and query-response capabilities.<n> deploying them in embedded and edge computing environments remains challenging because of strict latency, memory, and energy constraints.<n>We propose a hardware-aware, multi-objective structured pruning framework to address these limitations.
  arXiv  Detail & Related papers  (2026-06-08T09:38:13Z)
• A Comparative Study of CNN Optimization Methods for Edge AI: Exploring the Role of Early Exits [0.08209843760716957]
  This paper presents a unified deployment-oriented comparison of static compression and dynamic early-exit mechanisms.<n>Our results show that static and dynamic techniques offer fundamentally different trade-offs for edge deployment.<n>Their combination proves highly effective, simultaneously reducing inference latency and memory usage with minimal accuracy loss.
  arXiv  Detail & Related papers  (2026-04-16T08:50:49Z)
• Generative Control as Optimization: Time Unconditional Flow Matching for Adaptive and Robust Robotic Control [33.03635235189535]
  We introduce Generative Control as Optimization (GeCO), a time-unconditional framework that transforms action synthesis into iterative optimization.<n>Test-time inference becomes an adaptive process that allocates computation based on convergence-exiting early for simple states while refining longer for difficult ones.<n>We validate GeCO on standard simulation benchmarks and demonstrate seamless scaling to pi0-series Vision-Language-Action (VLA) models.
  arXiv  Detail & Related papers  (2026-03-18T15:27:17Z)
• DRAFTO: Decoupled Reduced-space and Adaptive Feasibility-repair Trajectory Optimization for Robotic Manipulators [4.0407133618465005]
  This paper introduces a new algorithm for trajectory optimization, Decoupled Reduced-space and Adaptive Feasibility-repair Trajectory Optimization (DRAFTO)<n>To reduce the number of repeated constrained optimizations while handling joint-limit feasibility, the optimization is decoupled into a reduced-space Gauss-Newton (GN) descent.<n>The results of our benchmark tests against optimization-based planners, such as CHOMP, TrajOpt, GPMP2, and FACTO, validate the high efficiency and reliability across diverse scenarios and tasks.
  arXiv  Detail & Related papers  (2026-03-10T20:24:42Z)
• Neural Nonmyopic Bayesian Optimization in Dynamic Cost Settings [73.44599934855067]
  LookaHES is a nonmyopic BO framework designed for dynamic, history-dependent cost environments.<n>LookaHES combines a multi-step variant of $H$-Entropy Search with pathwise sampling and neural policy optimization.<n>Our innovation is the integration of neural policies, including large language models, to effectively navigate structured, domain-specific action spaces.
  arXiv  Detail & Related papers  (2026-01-10T09:49:45Z)
• PT$^2$-LLM: Post-Training Ternarization for Large Language Models [52.4629647715623]
  Large Language Models (LLMs) have shown impressive capabilities across diverse tasks, but their large memory and compute demands hinder deployment.<n>We propose PT$2$-LLM, a post-training ternarization framework tailored for LLMs.<n>At its core is an Asymmetric Ternary Quantizer equipped with a two-stage refinement pipeline.
  arXiv  Detail & Related papers  (2025-09-27T03:01:48Z)
• Steerable Adversarial Scenario Generation through Test-Time Preference Alignment [58.37104890690234]
  Adversarial scenario generation is a cost-effective approach for safety assessment of autonomous driving systems.<n>We introduce a new framework named textbfSteerable textbfAdversarial scenario textbfGEnerator (SAGE)<n>SAGE enables fine-grained test-time control over the trade-off between adversariality and realism without any retraining.
  arXiv  Detail & Related papers  (2025-09-24T13:27:35Z)
• Learning Regions of Interest for Bayesian Optimization with Adaptive Level-Set Estimation [84.0621253654014]
  We propose a framework, called BALLET, which adaptively filters for a high-confidence region of interest. We show theoretically that BALLET can efficiently shrink the search space, and can exhibit a tighter regret bound than standard BO.
  arXiv  Detail & Related papers  (2023-07-25T09:45:47Z)
• ACE: Adaptive Constraint-aware Early Stopping in Hyperparameter Optimization [18.81207777891714]
  We propose an Adaptive Constraint-aware Early stopping (ACE) method to incorporate constraint evaluation into trial pruning during HPO. To minimize the overall optimization cost, ACE estimates the cost-effective constraint evaluation interval based on a theoretical analysis of the expected evaluation cost.
  arXiv  Detail & Related papers  (2022-08-04T22:56:16Z)
• Efficient Micro-Structured Weight Unification and Pruning for Neural Network Compression [56.83861738731913]
  Deep Neural Network (DNN) models are essential for practical applications, especially for resource limited devices. Previous unstructured or structured weight pruning methods can hardly truly accelerate inference. We propose a generalized weight unification framework at a hardware compatible micro-structured level to achieve high amount of compression and acceleration.
  arXiv  Detail & Related papers  (2021-06-15T17:22:59Z)
• You Only Compress Once: Towards Effective and Elastic BERT Compression via Exploit-Explore Stochastic Nature Gradient [88.58536093633167]
  Existing model compression approaches require re-compression or fine-tuning across diverse constraints to accommodate various hardware deployments. We propose a novel approach, YOCO-BERT, to achieve compress once and deploy everywhere. Compared with state-of-the-art algorithms, YOCO-BERT provides more compact models, yet achieving 2.1%-4.5% average accuracy improvement on the GLUE benchmark.
  arXiv  Detail & Related papers  (2021-06-04T12:17:44Z)
• Parallel Predictive Entropy Search for Multi-objective Bayesian Optimization with Constraints [0.0]
  Real-world problems often involve the optimization of several objectives under multiple constraints. This article introduces PPESMOC, an information-based batch method for the simultaneous optimization of black-box functions. Iteratively, PPESMOC selects a batch of input locations at which to evaluate the black-boxes.
  arXiv  Detail & Related papers  (2020-04-01T17:37:58Z)

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.