Unifying Depth and Width Pruning for LLMs via Binary Knapsack Optimization

• URL: http://arxiv.org/abs/2608.12953v1
• Date: Thu, 13 Aug 2026 08:32:18 GMT
• Title: Unifying Depth and Width Pruning for LLMs via Binary Knapsack Optimization
• Abstract summary: Structured pruning is a promising approach for compressing large language models (LLMs)<n>We present SNIPER, a two-stage structured pruning framework that solves a knapsack optimization over coarse-granularity components.<n>We demonstrate SNIPER's consistent improvements in average performance retention and task-level stability over six state-of-the-art pruners.
• Score: 22.700846957818687
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Structured pruning is a promising approach for compressing large language models (LLMs), yet existing methods rely heavily on greedy heuristics that produce myopic decisions, and often fail to precisely meet target compression budgets. We present SNIPER, a two-stage structured pruning framework that solves a knapsack optimization over coarse-granularity components to yield conditionally optimal parameter allocations with respect to fixed importance estimates, followed by a fine-grained pruning stage to meet strict budget constraints. We introduce the Compression Ratio Adherence Factor (CRAFT) to quantify budget fidelity, showing that while existing pruners deviate from target compression ratios by up to 33%, SNIPER achieves near-exact adherence with a CRAFT score of 0.98. Evaluations across four diverse architectures over a set of 18 tasks spanning five domains demonstrate SNIPER's consistent improvements in average performance retention and task-level stability over six state-of-the-art pruners. Across all pruning configurations, SNIPER achieves an excellent mean rank of 1.25, indicating its robust cross-architectural generalizability and excellent reliability.

Related papers

• Learn What's Left, Not What's Mastered: Saturation Aware Advantage Reweighting for Multi-Reward Policy Optimization [60.89431018071735]
  Reinforcement learning with group-relative advantages has become the de facto standard for post-training language model reasoners.<n>We show that rollouts with distinct reward profiles can receive identical advantages, and all objectives are optimized with fixed relative weights regardless of their current level of saturation.<n>We introduce saturation-aware reweighting, which standardizes each reward objective independently and adaptively discounts its contribution according to a batch-level estimate of objective saturation.
  arXiv  Detail & Related papers  (2026-08-17T04:07:50Z)
• Attribution-Guided and Coverage-Maximized Pruning for Structural MoE Compression [74.00650541246374]
  We propose a structural pruning framework tailored for MoE models.<n>Our approach reduces memory footprint by 5.27$times and consistently outperforms state-of-the-art baselines.
  arXiv  Detail & Related papers  (2026-06-16T06:53:27Z)
• Taming the Instability: A Robust Second-Order Optimizer for Federated Learning over Non-IID Data [77.19117648492104]
  We present Federated Robust Curvature Optimization (FedRCO), a novel second-order optimization framework designed to improve convergence speed and reduce communication cost.<n>FedRCO addresses these challenges by integrating an efficient approximate curvature with a provable stability mechanism.<n>We show that FedRCO achieves superior robustness against diverse non-IID scenarios while achieving higher accuracy and faster convergence than both state-of-the-art first-order and second-order methods.
  arXiv  Detail & Related papers  (2026-03-30T11:37:46Z)
• The Geometry of Robustness: Optimizing Loss Landscape Curvature and Feature Manifold Alignment for Robust Finetuning of Vision-Language Models [33.10473765967503]
  Generalization-preserving methods retain ID/OOD performance but leave models vulnerable to adversarial attacks.<n>Our key insight is that the robustness trade-off stems from two geometric failures: sharp, anisotropic minima in parameter space and unstable feature representations that deform under perturbation.<n>We propose GRACE, a unified fine-tuning framework that jointly regularizes the parameter-space curvature and feature-space invariance for VLMs.
  arXiv  Detail & Related papers  (2026-03-28T05:22:00Z)
• Towards Efficient Large Language Reasoning Models via Extreme-Ratio Chain-of-Thought Compression [55.63153956934198]
  Chain-of-Thought (CoT) reasoning successfully enhances the reasoning capabilities of Large Language Models (LLMs)<n>Existing CoT compression methods often suffer from a critical loss of logical fidelity at high compression ratios.<n>We propose a novel EXTreme-RAtio Chain-of-Thought Compression framework, termed Extra-CoT, which aggressively reduces the token budget while preserving answer accuracy.
  arXiv  Detail & Related papers  (2026-02-09T06:57:15Z)
• HQP: Sensitivity-Aware Hybrid Quantization and Pruning for Ultra-Low-Latency Edge AI Inference [0.0]
  Hybrid Quantization and Pruning (HQP) framework designed to achieve synergistic model acceleration.<n>HQP framework achieves a peak performance gain of 3.12 times inference speedup and a 55 percent model size reduction.
  arXiv  Detail & Related papers  (2026-02-02T18:17:45Z)
• ARMOR: High-Performance Semi-Structured Pruning via Adaptive Matrix Factorization [99.96330641363396]
  ARMOR: (Adaptive Representation with Matrix-factORization) is a novel one-shot post-training pruning algorithm.<n>Instead of directly pruning weights, ARMOR factorizes each weight matrix into a 2:4 sparse core wrapped by two low-overhead, block diagonal matrices.<n>We demonstrate ARMOR consistently and significantly outperforms state-of-the-art 2:4 pruning methods across a wide range of downstream tasks and perplexity evaluations.
  arXiv  Detail & Related papers  (2025-10-07T02:39:20Z)
• Týr-the-Pruner: Structural Pruning LLMs via Global Sparsity Distribution Optimization [16.627496870394456]
  T'yr-the-Pruner is an efficient end-to-end search-based global structural pruning framework.<n>We introduce an effective local pruning and an expectation error accumulation approach to improve supernet construction.<n>Results show that T'yr-the-Pruner achieves state-of-the-art structural pruning, retaining 97% of the dense model's performance.
  arXiv  Detail & Related papers  (2025-03-12T11:52:49Z)
• LoRAPrune: Structured Pruning Meets Low-Rank Parameter-Efficient Fine-Tuning [56.88751562302793]
  Low-rank adaption (LoRA) has emerged to fine-tune large language models (LLMs) LoRAPrune is a new framework that delivers an accurate structured pruned model in a highly memory-efficient manner. LoRAPrune achieves a reduction in perplexity by 4.81 on WikiText2 and 3.46 on PTB, while also decreasing memory usage by 52.6%.
  arXiv  Detail & Related papers  (2023-05-28T15:15:48Z)
• Evolving Pareto-Optimal Actor-Critic Algorithms for Generalizability and Stability [67.8426046908398]
  Generalizability and stability are two key objectives for operating reinforcement learning (RL) agents in the real world. This paper presents MetaPG, an evolutionary method for automated design of actor-critic loss functions.
  arXiv  Detail & Related papers  (2022-04-08T20:46:16Z)
• Certifiable Outlier-Robust Geometric Perception: Exact Semidefinite Relaxations and Scalable Global Optimization [29.738513596063946]
  We propose the first general framework to design cert algorithms for robust geometric perception in the presence of outliers. Our experiments demonstrate that our SDP relaxation is exact with up to outliers across applications.
  arXiv  Detail & Related papers  (2021-09-07T21:42:16Z)
• On the Structures of Representation for the Robustness of Semantic Segmentation to Input Corruption [16.897599251748982]
  Implicit Background Estimation (IBE) has demonstrated to be a promising technique to improve the robustness to out-of-distribution inputs for semantic segmentation models for little to no cost. In this paper, we provide analysis comparing the structures learned as a result of optimization objectives that use Softmax, IBE, and Sigmoid. We demonstrate that SCrIBE exhibits superior segmentation performance aggregated across all corruptions and severity levels with a mIOU of 42.1 compared to both IBE 40.3 and the Softmax Baseline 37.5.
  arXiv  Detail & Related papers  (2020-09-02T04:49:27Z)
• Adopting Robustness and Optimality in Fitting and Learning [4.511425319032815]
  We generalize a modified exponentialized estimator by pushing the robust-optimal (RO) index $lambda$ to $-infty digits. The robustness is realized and controlled adaptively by RONIST.
  arXiv  Detail & Related papers  (2015-10-13T19:14:43Z)

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.