Pith. sign in

REVIEW 3 cited by

Post-Training Statistical Calibration for Higher Activation Sparsity

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2412.07174 v1 pith:TOAWZZWE submitted 2024-12-10 cs.LG cs.AI

classification cs.LGcs.AI
keywords activationpost-trainingscapacrossmodelspruningsparsitystatistical
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

We present Statistical Calibrated Activation Pruning (SCAP), a post-training activation pruning framework that (1) generalizes sparsification by input activations of Fully-Connected layers for generic and flexible application across Transformers, and (2) features a simple Mode-Centering technique to pre-calibrate activation distributions for maximizing post-training sparsity. Our results demonstrate robust Pareto efficiency compared to prior methods, translating to a 1.5x additional LLM decoding speedup against CATS at iso model quality. SCAP effectiveness is empirically verified across a wide range of models, including recent Transformer Decoders, MoE, Mamba2, Encoding Transformer, and pre-quantized models, highlighting its practicality and scalability. The code is available at: https://github.com/IntelLabs/SCAP.

Discussion (0). Sign in to comment.

Forward citations

Cited by 3 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. Bug or Feature$^2$: Weight Drift, Activation Sparsity and Spikes

    cs.LG 2026-05 accept novelty 7.0 of 10

    Standard losses induce negative weight drift with positive-biased activations, producing up to 90% sparsity in GPT-nano and an accuracy cliff above ~70% sparsity; clipped ReLU² and GELU² improve the tradeoff.

  2. Bug or Feature$^2$: Weight Drift, Activation Sparsity and Spikes

    cs.LG 2026-05 accept novelty 7.0 of 10

    The paper proves negative weight drift at initialization under MSE or cross-entropy with asymmetric activations, links it to up to 90% sparsity in GPT-nano, maps the sparsity-accuracy cliff across 79 configurations, a...

  3. Motivating Next-Gen Accelerators with Flexible (N:M) Activation Sparsity via Benchmarking Lightweight Post-Training Sparsification Approaches

    cs.LG 2025-09 unverdicted novelty 5.0 of 10

    Post-training N:M activation pruning preserves generative performance in LLMs better than equivalent weight pruning, with the 8:16 pattern emerging as a practical hardware-friendly choice.

Pith tools