Adaptive Stochastic Natural Gradient Method for Safe Optimization on Binary Space

• URL: http://arxiv.org/abs/2605.17925v1
• Date: Mon, 18 May 2026 06:31:38 GMT
• Title: Adaptive Stochastic Natural Gradient Method for Safe Optimization on Binary Space
• Abstract summary: We propose a safe optimization method for binary search spaces based on the adaptive natural gradient method (ASNG)<n> safe ASNG computes a safe region that consists of safe solutions around the previously evaluated safe solutions.<n>By projecting newly generated solutions to their nearest neighbors within the safe region, safe ASNG suppresses unsafe solution evaluations.
• Score: 6.388430091498445
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Optimization problems in real-world applications across the medical and engineering domains often involve potential risks when evaluating candidate solutions. Safe optimization aims to perform optimization while suppressing unsafe solution evaluations in such situations. For continuous search spaces, there exist safe optimization methods based on evolutionary computation. However, the algorithm development of safe optimization methods for binary search spaces has not been adequately addressed. In this study, we incorporate additional mechanisms for safe optimization into a binary optimization method, the adaptive stochastic natural gradient method (ASNG) with a family of Bernoulli distributions. For safety functions that must be kept non-negative during optimization, the proposed method, safe ASNG, estimates the Lipschitz constants with respect to the Hamming distance by constructing surrogate models of safety functions based on discrete Walsh functions. Then, safe ASNG computes a safe region that consists of safe solutions around the previously evaluated safe solutions. By projecting newly generated solutions to their nearest neighbors within the safe region, safe ASNG suppresses unsafe solution evaluations. Experimental results on benchmark problems on binary domains confirm that, while the comparative methods fail to suppress unsafe solution evaluations, safe ASNG achieves efficient optimization while effectively suppressing unsafe solution evaluations.

Related papers

• Rethinking Safety in LLM Fine-tuning: An Optimization Perspective [56.31306558218838]
  We show that poor optimization choices, rather than inherent trade-offs, often cause safety problems, measured as harmful responses to adversarial prompts.<n>We propose a simple exponential moving average (EMA) momentum technique in parameter space that preserves safety performance.<n>Our experiments on the Llama families across multiple datasets demonstrate that safety problems can largely be avoided without specialized interventions.
  arXiv  Detail & Related papers  (2025-08-17T23:46:36Z)
• Safe Time-Varying Optimization based on Gaussian Processes with Spatio-Temporal Kernel [4.586346034304039]
  TVSafeOpt is an algorithm for time-varying optimization problems with unknown reward and safety functions. TVSafeOpt is capable of safely tracking a time-varying safe region without need for explicit change detection. We show that TVSafeOpt compares favorably against SafeOpt on synthetic data, both regarding safety and optimality.
  arXiv  Detail & Related papers  (2024-09-26T16:09:19Z)
• CMA-ES for Safe Optimization [9.130749109828717]
  This study focuses on CMA-ES as an efficient evolutionary algorithm and proposes an optimization method termed safe CMA-ES. The safe CMA-ES is designed to achieve both safety and efficiency in safe optimization.
  arXiv  Detail & Related papers  (2024-05-17T04:24:56Z)
• Information-Theoretic Safe Bayesian Optimization [59.758009422067005]
  We consider a sequential decision making task, where the goal is to optimize an unknown function without evaluating parameters that violate an unknown (safety) constraint. Most current methods rely on a discretization of the domain and cannot be directly extended to the continuous case. We propose an information-theoretic safe exploration criterion that directly exploits the GP posterior to identify the most informative safe parameters to evaluate.
  arXiv  Detail & Related papers  (2024-02-23T14:31:10Z)
• Bayesian Optimization with Formal Safety Guarantees via Online Conformal Prediction [36.14499894307206]
  Black-box zero-th order optimization is a central primitive for applications in fields as diverse as finance, physics, and engineering. In this paper, we study scenarios in which feedback is also provided on the safety of the attempted solution. A novel BO-based approach is introduced that satisfies safety requirements irrespective of properties of the constraint function.
  arXiv  Detail & Related papers  (2023-06-30T17:26:49Z)
• Adaptive Real Time Exploration and Optimization for Safety-Critical Systems [0.0]
  We propose the ARTEO algorithm, where we cast multi-armed bandits as a programming problem subject to safety constraints. We learn the environmental characteristics through changes in optimization inputs and through exploration. Compared to existing safe-learning approaches, our algorithm does not require an exclusive exploration phase and follows the optimization goals even in the explored points.
  arXiv  Detail & Related papers  (2022-11-10T11:37:22Z)
• Generalizing Bayesian Optimization with Decision-theoretic Entropies [102.82152945324381]
  We consider a generalization of Shannon entropy from work in statistical decision theory. We first show that special cases of this entropy lead to popular acquisition functions used in BO procedures. We then show how alternative choices for the loss yield a flexible family of acquisition functions.
  arXiv  Detail & Related papers  (2022-10-04T04:43:58Z)
• Log Barriers for Safe Black-box Optimization with Application to Safe Reinforcement Learning [72.97229770329214]
  We introduce a general approach for seeking high dimensional non-linear optimization problems in which maintaining safety during learning is crucial. Our approach called LBSGD is based on applying a logarithmic barrier approximation with a carefully chosen step size. We demonstrate the effectiveness of our approach on minimizing violation in policy tasks in safe reinforcement learning.
  arXiv  Detail & Related papers  (2022-07-21T11:14:47Z)
• Safe Policy Optimization with Local Generalized Linear Function Approximations [17.84511819022308]
  Existing safe exploration methods guaranteed safety under the assumption of regularity. We propose a novel algorithm, SPO-LF, that optimize an agent's policy while learning the relation between a locally available feature obtained by sensors and environmental reward/safety. We experimentally show that our algorithm is 1) more efficient in terms of sample complexity and computational cost and 2) more applicable to large-scale problems than previous safe RL methods with theoretical guarantees.
  arXiv  Detail & Related papers  (2021-11-09T00:47:50Z)
• Optimistic Policy Optimization is Provably Efficient in Non-stationary MDPs [113.8752163061151]
  We study episodic reinforcement learning (RL) in non-stationary linear kernel Markov decision processes (MDPs)<n>We propose the underlineperiodically underlinerestarted underlineoptimistic underlinepolicy underlineoptimization algorithm (PROPO)<n>PROPO features two mechanisms: sliding-window-based policy evaluation and periodic-restart-based policy improvement.
  arXiv  Detail & Related papers  (2021-10-18T02:33:20Z)
• Chance-Constrained Trajectory Optimization for Safe Exploration and Learning of Nonlinear Systems [81.7983463275447]
  Learning-based control algorithms require data collection with abundant supervision for training. We present a new approach for optimal motion planning with safe exploration that integrates chance-constrained optimal control with dynamics learning and feedback control.
  arXiv  Detail & Related papers  (2020-05-09T05:57:43Z)

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.