Maria Matveev, Pascal Esser, Ayush Bharadwaj +2cs.LG
A central question in modern machine learning is how much a trained model can be compressed without changing its behavior, to reduce the memory, compute and energy required to deploy it. To study this, we quantify functional degeneracy through the behavioral recovery rank, defined as the number of leading behavioral-Hessian eigendirections required to recover a trained model's performance. Using the behavioral recovery rank as a geometric benchmark for compression, we find that structural and magnitude pruning retain more degrees of freedom, even after the task is saturated. This gap suggests that functional redundancy is distributed across parameter directions and is not exposed by individual weights or neurons.
Split conformal prediction, not the pruning rule, supplies finite-sample marginal coverage once a pruned model is fixed independently of the conformal calibration split. We study the separate efficiency problem: can pruning preserve score geometry well enough to obtain smaller valid prediction sets? Calibration-Preserving Pruning (CPP) augments a base pruning score with nonconformity-gradient saliency and uses disjoint pruning, validation-selection, conformal-calibration, and test splits. Bounded score perturbations imply bounded conformal-quantile shifts and controlled set inflation, but do not make the generic coverage theorem CPP-specific. Final five-seed Qwen2.5-1.5B results at 50\% sparsity show the largest gains on large-label tasks. On DBpedia-14, CPP-SparseGPT reduces mean set size from \(10.1\) to \(8.6\) while changing accuracy from \(0.347\) to \(0.366\); CPP-Wanda reduces \(11.2\) to \(9.0\) with an accuracy trade-off from \(0.310\) to \(0.295\). Across 15 dataset--sparsity cells, CPP-SparseGPT produces smaller sets in 13 and higher accuracy in 11. Matched controls show that generic supervised gradients explain much of the gain: true-label CPP is not statistically resolved from matched Wanda+SNIP, whereas threshold-aware candidate-label CPP reaches \(7.8\) mean set size at explicit accuracy and offline-compute costs. RoBERTa-base and Llama-3-8B diagnostics support transfer, but our claims remain limited to reliability-sensitive classification.
Semi-structured $N$:$M$ sparsity has emerged as a practical direction for accelerating large language models (LLMs). However, existing learnable-mask approaches incur substantial parameter and memory overhead, limiting their scalability to large models and aggressive sparsity regimes. In this work, we revisit semi-structured pruning from a perspective that reconciles efficiency with scalability. We propose Reservoir of Importance (RoI), a lightweight semi-structured pruning framework that learns sparsity masks through differentiable subset sampling. Unlike prior methods that model full categorical distributions over all feasible $N$:$M$ patterns, RoI introduces a compact-logit parameterization for sparsity mask learning and performs sampling without replacement to select masks, thereby reducing trainable parameters from combinatorial complexity to $\mathcal{O}({M})$. As a result, RoI requires 1.5-8.75$\times$ fewer learnable parameters and significantly lower memory cost, while remaining fully aligned with hardware-friendly sparsity patterns. Extensive evaluations across multiple scales of the Qwen2.5 LLM family (0.5-7B parameters) demonstrate that RoI achieves competitive performance with strong memory efficiency, stability, and scalability to more aggressive $N$:$M$ sparsity patterns, offering a practical path toward efficient LLM deployment.
Model compression is critical for deploying networks on resource-constrained edge devices. While pruning-based methods can significantly reduce model size, they often suffer from abrupt performance collapse beyond a sparsity thresh-old, making it difficult to identify the feasible compression limit of the model. To address this challenge, we propose a boundary-Learning reverse regrowth framework, BRIDGE, that reformulates compression as a constructive boundary-search problem. Unlike forward pruning, our method first drives the model to an extremely sparse state to expose the collapse region, and then selectively regenerates the critical structure to restore performance. The proposed framework employs a hierarchical regeneration strategy, including coarse-grained layer selection and fine-grained regeneration parameter selection, to accurately identify which parameters require recovery. Experiments show that our method can recover models from the brink of collapse on both CNNs and Transformer architectures, demonstrating its architecture in-dependence. BRIDGE achieves a performance improvement of up to 1.49% in unstructured pruning and up to 4.77% in structured pruning. These results demonstrate that reverse regeneration can effectively extend the compression limit while maintaining stable performance. The source code is available at https://github.com/EnumaCaliber/BRIDGE.
Running large AI models on resource-constrained edge devices requires model compression to reduce model size and computation. What compresses well, however, need not deploy well. We survey dozens of recent works that report compression results on real hardware and extract practical deployment guidelines from them. Following these guidelines, we deploy compact language and image models on GPU, CPU, and Raspberry Pi platforms across question answering and image segmentation. No single technique wins across tasks. For question answering, Qwen3.5 0.8B reaches 93.85 SQuAD F1 and 92 EM under Q5_K_M GGUF quantization, while structured pruning at the same precision costs 16 F1 at a 1% ratio. For segmentation, the ranking reverses: default quantization leaves parameters and MACs unchanged, whereas pruning cuts model size by nearly 80% at near-constant mIoU. Pruning can even inflate the deployed artifact by 21-49% by breaking k-quant super-block alignment; combined with longer, less format-compliant outputs, this raises Raspberry Pi latency up to 3.4x. Compression can also manufacture the appearance of competence rather than destroy it visibly: one LoRA-recovered variant stays fully parseable and holds 71% strict BoolQ accuracy while sending 97 of 100 predictions to a single class, at 52.6% balanced accuracy. We explain these effects through neural-flow graph analysis and prefill-decode-level latency decomposition, and condense them into task-specific deployment research directions. The right technique depends on the task, the model, and the hardware. Our experiment code and artifacts are open-sourced at https://github.com/Arnavvvkumar/deployment
Long-context inference with large language models is constrained by the linear growth of the key-value cache to sequence length. While pruning offers mitigation, prevailing methods determine query-specific token importance that cannot be reused across unseen queries. In contrast, we introduce TaskPress, a framework for task-guided, query-agnostic KV cache eviction. Instead of optimizing the cache for a single query, TaskPress constructs a reusable memory representation conditioned on a high-level task guide. The guide functions as a meta-query during prefill to filter irrelevant tokens before downstream queries are issued. In addition, TaskPress leverages quantization scale factors as a zero-cost signal for detecting influential representation outliers, providing an efficient proxy for token importance. Experiments on conducted on various tasks with long context input demonstrate that TaskPress efficiently creates a compact, reusable cache across diverse queries.
One-shot post-training pruning is the most energy-frugal compression strategy for largelanguage models (LLMs), yet existing approaches trade either quality (WANDA) or compute cost (SPARSEGPT). We introduce F-WANDA, a drop-in modification of WANDA that reallocates the per-row keep budget across output neurons in proportion to the empirical Fisher information of the pre-activation. The Fisher signal is collected in a single additional backward pass over the same calibration corpus WANDA already uses; no weights are updated. On LLAMA-2-7B at 50 % unstructured sparsity, F-WANDA attains WikiText-2 perplexity of 6.85, matches WANDA fluency, and improves 5-shot MMLU by +1.6 pp over WANDA and +1.1 pp over SPARSEGPT, while incurring only one-third of SPARSEGPT pruning wall-clock and energy. The headline trade-off is achieved without extra calibration data or fine-tuning, placing F-WANDA on the Pareto frontier of quality versus pruning cost for sustainable LLM compression.
Hossein Mobahi, Peter L. Bartlettcs.LG cs.AI stat.ML
Deep neural networks encode complex representations, but deconstructing this internal knowledge remains a challenge. Given the link between learning and compression, network compression offers a promising lens to analyze this knowledge. However, standard compression heuristics often suffer from scale symmetries and architectural biases. To resolve these, we introduce Hilbert Operator for Progressive Encoding (HOPE), a mathematical framework to gradually deconstruct the representations in trained network weights. HOPE shifts network compression from the discrete domain into a Hilbert space of continuous functions. By modeling individual neurons as rank-1 Hilbert-Schmidt operators, HOPE unifies pruning and neuron merging as low-rank subspace projection. Extending this formulation, HOPE introduces macro block eviction to encompass multi-layer structures like entire residual pathways under the same unified metric. This unified approach enables unbiased architectural decisions across layers with different types and sizes. HOPE is a data-free and hyperparameter-free framework. We present proof-of-concept experiments in model compression and fine-tuning to highlight the practical potential of our theory.
Large language models (LLMs) are often compressed through static parameter pruning or dynamic token-level computation, yet aggressive sparsification can trigger rapid performance degradation beyond an essential sparsity boundary. This work asks \emph{whether combining these two mechanisms can delay such degradation by distributing the compression burden}. We study a minimalist compound sparsity framework that first applies low-rank approximation and channel pruning to obtain a statically compressed backbone, and then introduces lightweight routers for per-token dynamic layer skipping. This design enables independent control of parameter sparsity and token-level computation sparsity. Experiments across language understanding and modeling benchmarks show that compound sparsity consistently outperforms single-mechanism compression under the same total sparsity, delaying the decay point on understanding tasks and preserving stronger modeling performance. Further analysis reveals cross-dimensional interference between parameter pruning and token skipping, and shows that near-balanced allocation is most effective under a fixed sparsity budget. These results demonstrate that compound compression provides a practical way to improve LLM compression, while revealing a broader cross-dimensional sparsity boundary that ultimately limits further compression. Code will be available at https://github.com/EIT-NLP/LLM-Pruning.
Mixture-of-Experts (MoE) language models scale model ability with sparsely activated experts, making this architecture a standard recipe for modern large models. However, sparse activation does not remove the deployment burden of storing and serving all experts, and the available deployment budget can vary substantially across devices, users, and workloads. Existing MoE compression methods are still largely fixed-budget, typically optimizing one compressed endpoint at each chosen target budget. We study a different setting: converting a large pretrained MoE LLM into a nested family of deployable subnetworks across budgets. Our method first ranks expert FFN channels by their importance, then lets each expert learn a discrete action to prune its channels. By gradually increasing cost pressure, a single action-training run exports a series of action masks from high to low budgets, each of which identifies a reliable smaller subnetwork nested in the ranked base model. Moreover, we use a single recovery fine-tune at a mid pruning budget (40%) to recover degraded model quality and transfer the recovered model to other unseen budgets. Overall, our framework surpasses recent MoE compression baselines. Specifically, on Qwen2-57B-A14B, our method retains ~99.8% of base performance while pruning 50% of routed expert parameters even without fine-tuning. For deployment, our pruned subnetworks deliver real memory reduction and throughput gains, and further support realtime online budget switching with kernel-level co-design.
Deploying spiking neural networks (SNNs) on neuromorphic hardware demands aggressive synaptic pruning while preserving temporal computation integrity. Existing strategies either neglect neuronal criticality or rely on convex relaxations of the inherently combinatorial pruning problem whose fractional masks, upon binarisation, destroy accuracy at moderate-to-high sparsity. We present Criticality-Constrained Quadratic Pruning (CQP), a native PyTorch pipeline that fuses weight magnitude with surrogate-gradient criticality into an analytically exact importance metric, eliminating the rounding artefacts endemic to solver-based approaches. We formally characterise a continuous-relaxation trap wherein OSQP-solver fractional masks overshoot the intended sparsity by up to 12 percentage points (pp), precipitating a 44 pp accuracy collapse. We identify and remediate a zombie-weight failure mode in which Adam's first-moment tensors resurrect pruned synapses, violating the binary sparsity guarantee. An iterative schedule - prune, fine-tune with gradient masking, recompute criticality, and repeat - eliminates gradient staleness at high sparsity. A KL-divergence temporal analysis identifies a redundant simulation timestep, enabling a free 10% theoretical energy reduction without weight modification. On MNIST (60,000 training examples), CQP yields 95.6% accuracy at 90% sparsity versus 93.4% for magnitude pruning (+2.2 pp). A criticality-threshold sweep reveals an empirical criticality cliff: accuracy falls from 87.0% to 14.4% as the threshold reaches tau = 0.9, constituting a quantitative SNN-level analogue of the Critical Brain Hypothesis. Combined weight sparsification and temporal truncation yield a compound 73% reduction in per-inference energy at 70% sparsity, confirming the practical value of the proposed pipeline for neuromorphic deployment.
We present HiReLC, a hierarchical ensemble-reinforcement learning framework for automated joint quantization and structured pruning of deep neural networks. The framework decomposes the compression search across two levels of abstraction: low-level agents (LLAs) operate independently per block, selecting per-kernel configurations over a multi-discrete action space spanning bitwidth, pruning keep-ratio, quantization type, and granularity, while high-level agents (HLAs) coordinate global budget allocation via ensemble voting guided by Fisher Information-based sensitivity estimates. To mitigate the computational cost of policy evaluation, an iterative active learning loop interleaves surrogate-guided RL optimization with post-compression fine-tuning, using a lightweight MLP surrogate to amortize expensive evaluations and a logit-MSE proxy during cold-start. The surrogate is used for reward shaping rather than as a replacement for final post-compression evaluation. The controller is architecture-agnostic by design, with a modular layer abstraction decoupling the RL environment from the underlying network topology. Experiments across Vision Transformer and CNN benchmarks demonstrate effective parameter-storage compression ratios of 5.99 - 6.72$\times$ with a 3.83 % gain in one setting and 0.55 - 5.62 % accuracy drops elsewhere, supporting hierarchical policy decomposition and sensitivity-aware guidance as practical design choices for joint neural network compression.
Large Language Models (LLMs) achieve strong performance across a growing range of domains, yet their scale poses deployment challenges in applications where latency and cost constraints are critical. This paper derives empirical scaling laws for domain-specific LLM compression, quantifying how in-domain and general knowledge performance scale with dataset size, compression ratio, supervision format, and iterative pruning schedule. Using quantitative finance as our application domain, we compare logit-based and LoRA-based distillation under iterative structural pruning, introducing a blended chain-of-thought supervision loss that stabilizes KL-divergence distillation over reasoning traces. In-domain task quality degrades predictably under compression while general-knowledge benchmarks collapse well before the same point; supervision format is the key driver of this tradeoff, with chain-of-thought supervision actively recovering general knowledge that pruning erases. We release the headline dataset FinHeadlineMix, scaling law results, and practical recommendations to provide a reusable framework for domain-specific compression decisions.
Deep neural networks have witnessed remarkable advancements in recent years and have become integral to various applications. However, alongside these developments, training and deployment of neural network models on embedding and edge devices face significant challenges due to limited memory and computational resources. These problems can be addressed with deep neural network compression, which involves a trade-off between model size and performance. In this paper, we propose a novel method for model compression through two phases. First, we utilize model compression techniques, such as pruning and quantization, to significantly reduce the model size. Then, we use Mixture of Experts to route the previously compressed models to enhance performance while maintaining a balance in inference efficiency. MoEs consist of multiple expert models (i.e., compressed models) that are moderately sized and deliver stable performance. Experimental results on several benchmark datasets show that our method successfully compresses CNN models which achieves substantial reductions in FLOPs and parameters with a negligible accuracy drop.
Mixture-of-Experts (MoE) models scale compute efficiently, yet remain expensive to deploy due to their substantial memory footprint and inference overhead. Prior compression methods mainly operate at the expert level, either removing entire experts or ranking experts by coarse-grained importance scores. However, such expert-wise decisions are often too coarse to capture fine-grained redundancy, leading to misallocated pruning budgets and limited compression. To address this problem, we observe that information within MoE experts is highly concentrated in a small subset of channels, leaving substantial redundancy even in experts deemed important. Based on this observation, we propose a structural pruning framework tailored for MoE models. Our method reformulates prune-ratio allocation as a channel-score coverage maximization problem and solves it efficiently using an attribution-based approximation. Experiments on DeepSeek and Qwen MoE models show that our method preserves model accuracy under 50% or 25% structured pruning when combined with 4-bit quantization. On Qwen3-30B-A3B, our approach reduces memory footprint by 5.27$\times$ and consistently outperforms state-of-the-art baselines across diverse benchmarks.
Roman Denkin, Ida Akerholm, Prashant Singh +1cs.LG cs.AI
Unstructured pruning produces sparse weight tensors, but the standard implementation keeps tensor shapes unchanged so the deployed model is no smaller than before pruning. We present an exact structural rewrite, which we call minimization, that converts a masked network into a smaller dense network with the same forward function up to floating-point rounding. The Squeeze-Release cycle iterates pruning and minimization with an intermediate release step that re-enables the exact-zero positions inside the compacted tensors as small calibrated noise, turning otherwise wasted capacity back into trainable parameters. Successive cycles use that capacity to find structural redundancy a single pass cannot reach. We additionally introduce CompensatedLayerNorm, a function-preserving replacement for LayerNorm that extends minimization to channel reduction across LayerNorm-equipped residual streams. Squeeze-Release compresses the deployable network to 39x smaller than the unpruned model on a fully-connected model network and 14.8x smaller on modern CNN (ConvNeXt-Tiny), at comparable accuracy. In addition we prove that the rewrite can be extended to transformer architectures.
Mixture-of-Experts large language models (LLMs) scale efficiently through sparse activation, yet their deployment is fundamentally constrained by the large static parameter footprint of experts. Existing compression approaches either remove entire experts, disrupting routing topology and harming performance, or rely on unstructured weight pruning with limited practical efficiency. To address the limitations, we propose TENP, a structured Trapezoidal ExpertNeuron Pruning framework. Using a few samples, we identify and retain important experts, while applying expert neuron pruning (ENP) to less important experts, reserving model parameters in a trapezoidal pattern from shallow to deep layers. When evaluating expert importance, we jointly consider both the magnitude of the expert output and its ability to change the direction of the input vector. For ENP, we measure each neuron's projected contribution to the expert output to identify and retain important neurons. We conduct extensive experiments on the Qwen and DeepSeek models. Under a routing expert sparsity of 40% and an average of 63.76% activated expert parameters, the DeepSeek model suffers only a 1-point drop in accuracy compared to the full-parameter model. Moreover, it outperforms the full-parameter model by 10% on code generation tasks.
Model compression techniques such as quantization and pruning are widely used to reduce the deployment cost of large language models (LLMs), with existing evaluations focusing almost exclusively on accuracy preservation. However, in safety-critical applications, a model's ability to reliably quantify its own uncertainty is equally important. We ask: does compression preserve this ability? To answer this question, we benchmark 12 LLMs under various compression configurations across five NLP tasks, using conformal prediction to provide a rigorous, distribution-free measure of uncertainty. Our experiments reveal that: (I) compression frequently decouples accuracy from uncertainty; (II) larger models absorb compression-induced uncertainty far more effectively than smaller ones; and (III) uncertainty inflation is often threshold-like rather than gradual. These results suggest that accuracy-only evaluation is insufficient for assessing the deployment readiness of compressed LLMs, and that uncertainty-aware benchmarking should be a standard component of model compression pipelines.