Track papers across labs, topics, and trends.
Search papers, labs, and topics across Lattice.
This paper introduces a constraint-driven framework for model optimization in machine learning, addressing the challenges practitioners face when selecting among various techniques like quantization and pruning. By framing optimization as a multi-objective engineering decision across five key constraints—data availability, latency, memory, accuracy, and retraining budgets—the authors provide a structured approach that synthesizes empirical gains from existing literature. The proposed framework not only clarifies the relationship between operational constraints and optimization techniques but also includes practical optimization pipelines for real-world industrial scenarios.
A unified framework reveals how to navigate the complex landscape of model optimization by aligning techniques with critical operational constraints.
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.