arXiv:2607.13735v2 Announce Type: replace 
Abstract: The rapid deployment of machine learning systems across cloud, edge, and enterprise environments has brought model optimization to the forefront of systems-engineering. Despite a rich literature spanning quantization, pruning, knowledge distillation, parameter-efficient fine-tuning (PEFT), and inference-time optimization, practitioners are often left navigating these techniques through heuristics rather than principled methodology. We argue that optimization should be formulated as a constraint-driven, multi-objective engineering decision and introduce a unified framework that characterizes any production deployment along five interacting constraint dimensions: data availability, latency budget, memory budget, accuracy tolerance, and retraining budget. Building on this taxonomy, we synthesize empirical gains reported across the research literature and map them to operational constraints rather than algorithmic categories. To ensure practical relevance, we selected these techniques by reviewing recent literature for methods that report measurable improvements against critical deployment bottlenecks. We propose a prescriptive decision framework and provide optimization pipelines for four representative industrial scenarios to illustrate it in practice. To the best of our knowledge, this work provides one of the first structured attempts to formalize model optimization as a constraint-aware, multi-objective engineering process, synthesizing quantitative evidence from the research literature.

تنشر المقالة الأخيرة حول تحسين النماذج المدفوعة بالقيود إطارًا موحدًا لاختيار تقنيات الضغط والتسريع في أنظمة التعلم الآلي، مما يبرز الحاجة إلى نهج منهجي وسط تنوع طرق التحسين المتاحة.

La reciente publicación sobre optimización de modelos impulsada por restricciones presenta un marco unificado para seleccionar técnicas de compresión y aceleración en sistemas de aprendizaje automático, enfatizando la necesidad de un enfoque metódico en medio de la diversidad de métodos de optimización disponibles.

La récente publication sur l'optimisation des modèles basée sur des contraintes présente un cadre unifié pour sélectionner les techniques de compression et d'accélération dans les systèmes d'apprentissage automatique, soulignant la nécessité d'une approche méthodique face à la diversité des méthodes d'optimisation disponibles.

The recent publication on constraint-driven model optimization presents a unified framework for selecting compression and acceleration techniques in machine learning systems, emphasizing the need for a principled approach amidst the diverse optimization methods available.