Post-Training Probability Manifold Correction via Structured SVD Pruning and Self-Referential Distillation

• URL: http://arxiv.org/abs/2602.00372v1
• Date: Fri, 30 Jan 2026 22:42:02 GMT
• Title: Post-Training Probability Manifold Correction via Structured SVD Pruning and Self-Referential Distillation
• Abstract summary: We introduce Sparse Knowledge Distillation (SparseKD), a method that compresses transformer models by combining structured SVD pruning with self-referential knowledge distillation.<n>SparseKD requires no external super-teacher, no architectural changes, and no custom inference kernels, making it immediately deployable with existing infrastructure.
• Score: 0.0
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Large language models are expensive to deploy. We introduce Sparse Knowledge Distillation (SparseKD), a post-training method that compresses transformer models by combining structured SVD pruning with self-referential knowledge distillation. The key insight is simple: instead of using an external teacher, the model teaches itself by matching its own probability distribution from before compression. This self-referential setup enables surprisingly strong quality recovery after aggressive pruning. Our experiments reveal an unexpected finding: self-referential distillation alone, applied post-training under an identical objective and fixed calibration dataset, improves model quality by 39% relative to the original converged checkpoint. When combined with structured pruning, SparseKD achieves 15-65% parameter reduction with acceptable quality trade-offs. Kernel profiling shows that speedups arise entirely from reduced dense matrix multiplication in feed-forward layers while attention remains unchanged, making this approach complementary to attention optimizations. We validate across two model families (0.6B and 3.8B parameters) with multi-seed experiments confirming high reproducibility. SparseKD requires no external super-teacher, no architectural changes, and no custom inference kernels, making it immediately deployable with existing infrastructure.

Related papers

• MixSD: Mixed Contextual Self-Distillation for Knowledge Injection [29.7616760417696]
  Supervised fine-tuning (SFT) is widely used to inject new knowledge into language models.<n>We argue this forgetting arises because fine-tuning targets from humans or external systems diverge from the model's autoregressive distribution.<n>We propose MixSD, a simple external-teacher-free method for distribution-aligned knowledge injection.
  arXiv  Detail & Related papers  (2026-05-16T07:57:09Z)
• Multimodal Learning on Low-Quality Data with Conformal Predictive Self-Calibration [72.0672328514289]
  Multimodal learning often grapples with the challenge of low-quality data.<n>We propose a unified framework, termed Conformal Predictive Self-Calibration.<n>Our framework consistently outperforms existing state-of-the-art methods.
  arXiv  Detail & Related papers  (2026-05-05T14:48:52Z)
• Perturb and Correct: Post-Hoc Ensembles using Affine Redundancy [0.0]
  We introduce Perturb-and-Correct (P&C), a method for constructing diverse predictors from a single pretrained network.<n>P&C applies random hidden layer perturbations with a least-squares correction in the subsequent affine layer, producing predictors that agree on calibration data while remaining free to disagree away from it.<n> Empirically, P&C achieves a strong ID/OOD tradeoff across MuJoCo dynamics prediction and CIFAR-10 OOD detection, matching or outperforming standard post-hoc baselines while requiring only a single pretrained model.
  arXiv  Detail & Related papers  (2026-05-02T22:48:11Z)
• When Perplexity Lies: Generation-Focused Distillation of Hybrid Sequence Models [18.966595547209824]
  We propose a Hybrid Kimi Delta Attention (Hybrid-KDA) architecture paired with GenDistill.<n>We find that log-likelihood-based evaluation consistently underestimates the gap between teacher and student.
  arXiv  Detail & Related papers  (2026-03-27T16:16:23Z)
• Temper-Then-Tilt: Principled Unlearning for Generative Models through Tempering and Classifier Guidance [51.532841645285835]
  We study machine unlearning in large generative models by framing the task as density ratio estimation to a target distribution.<n>We show it can fail to faithfully unlearn with finite samples when the forget set represents a sharp, concentrated data distribution.<n>We introduce Temper-Then-Tilt Unlearning (T3-Unlearning), which freezes the base model and applies a two-step inference procedure.
  arXiv  Detail & Related papers  (2026-02-10T19:08:40Z)
• ALoRE: Efficient Visual Adaptation via Aggregating Low Rank Experts [71.91042186338163]
  ALoRE is a novel PETL method that reuses the hypercomplex parameterized space constructed by Kronecker product to Aggregate Low Rank Experts.<n>Thanks to the artful design, ALoRE maintains negligible extra parameters and can be effortlessly merged into the frozen backbone.
  arXiv  Detail & Related papers  (2024-12-11T12:31:30Z)
• Adaptive Gradient Clipping for Robust Federated Learning [8.268485501864939]
  We propose a principled adaptive clipping strategy, Adaptive Robust Clipping (ARC), which dynamically adjusts clipping thresholds based on the input gradients.<n>ARC significantly enhances robustness, particularly in highly heterogeneous and adversarial settings.
  arXiv  Detail & Related papers  (2024-05-23T11:00:31Z)
• Noisy Correspondence Learning with Self-Reinforcing Errors Mitigation [63.180725016463974]
  Cross-modal retrieval relies on well-matched large-scale datasets that are laborious in practice. We introduce a novel noisy correspondence learning framework, namely textbfSelf-textbfReinforcing textbfErrors textbfMitigation (SREM)
  arXiv  Detail & Related papers  (2023-12-27T09:03:43Z)
• Learnable Distribution Calibration for Few-Shot Class-Incremental Learning [122.2241120474278]
  Few-shot class-incremental learning (FSCIL) faces challenges of memorizing old class distributions and estimating new class distributions given few training samples. We propose a learnable distribution calibration (LDC) approach, with the aim to systematically solve these two challenges using a unified framework.
  arXiv  Detail & Related papers  (2022-10-01T09:40:26Z)
• Few-Shot Non-Parametric Learning with Deep Latent Variable Model [50.746273235463754]
  We propose Non-Parametric learning by Compression with Latent Variables (NPC-LV) NPC-LV is a learning framework for any dataset with abundant unlabeled data but very few labeled ones. We show that NPC-LV outperforms supervised methods on all three datasets on image classification in low data regime.
  arXiv  Detail & Related papers  (2022-06-23T09:35:03Z)
• Distributionally Robust Models with Parametric Likelihood Ratios [123.05074253513935]
  Three simple ideas allow us to train models with DRO using a broader class of parametric likelihood ratios. We find that models trained with the resulting parametric adversaries are consistently more robust to subpopulation shifts when compared to other DRO approaches.
  arXiv  Detail & Related papers  (2022-04-13T12:43:12Z)
• Self-Distillation from the Last Mini-Batch for Consistency Regularization [14.388479145440636]
  We propose an efficient and reliable self-distillation framework, named Self-Distillation from Last Mini-Batch (DLB) Our proposed mechanism guides the training stability and consistency, resulting in robustness to label noise. Experimental results on three classification benchmarks illustrate that our approach can consistently outperform state-of-the-art self-distillation approaches.
  arXiv  Detail & Related papers  (2022-03-30T09:50:24Z)
• Distribution Mismatch Correction for Improved Robustness in Deep Neural Networks [86.42889611784855]
  normalization methods increase the vulnerability with respect to noise and input corruptions. We propose an unsupervised non-parametric distribution correction method that adapts the activation distribution of each layer. In our experiments, we empirically show that the proposed method effectively reduces the impact of intense image corruptions.
  arXiv  Detail & Related papers  (2021-10-05T11:36:25Z)
• Re-parameterizing VAEs for stability [1.90365714903665]
  We propose a theoretical approach towards the training numerical stability of Variational AutoEncoders (VAE) Our work is motivated by recent studies empowering VAEs to reach state of the art generative results on complex image datasets. We show that by implementing small changes to the way we parameterize the Normal distributions on which they rely, VAEs can securely be trained.
  arXiv  Detail & Related papers  (2021-06-25T16:19:09Z)
• Even your Teacher Needs Guidance: Ground-Truth Targets Dampen Regularization Imposed by Self-Distillation [0.0]
  Self-distillation, where the network architectures are identical, has been observed to improve generalization accuracy. We consider an iterative variant of self-distillation in a kernel regression setting, in which successive steps incorporate both model outputs and the ground-truth targets. We show that any such function obtained with self-distillation can be calculated directly as a function of the initial fit, and that infinite distillation steps yields the same optimization problem as the original with amplified regularization.
  arXiv  Detail & Related papers  (2021-02-25T18:56:09Z)

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.