arXiv Machine Learning

Neural Spectral Capacity: Measuring and Designing Architectures from Network Specification Alone

The paper introduces Neural Spectral Capacity (NSC), a closed‑form metric derived from the singular‑value spectrum of weight matrices that can be computed solely from a network’s architectural specification. Unlike traditional measures such as #Params and #FLOPs, NSC captures architectural structure (depth, width, head, FFN allocations) and can be evaluated without instantiating the model, data, or gradients. Using a dynamic‑programming solver (NSC‑DP), the authors demonstrate that NSC can efficiently identify architectures that outperform existing training‑free proxies across Transformer and CNN families, and achieve state‑of‑the‑art results in tasks such as WikiText‑103 and commonsense reasoning with LLaMA‑7B. whyItMatters":"NSC provides a fast, architecture‑only proxy that outperforms conventional metrics and training‑free proxies, enabling more effective design and pruning of large models without costly training or data."

arXiv Machine Learning
Oct 23

Neural Spectral Capacity with Residual Context for Heterogeneous Resource Allocation within Transformers

The paper introduces Residual-Aware Neural Spectral Capacity (ResNSC) for Transformers, enhancing the original NSC heuristic by incorporating residual updates into capacity calculations. ResNSC-DP jointly allocates residual and feed‑forward widths under a resource budget, providing certified bounds on the best achievable ResNSC score. Experiments on 121M and 374M models show that architectures selected by ResNSC-DP achieve lower perplexity than uniform or tapered allocations, and in LLaMA‑7B pruning ResNSC-DP improves average accuracy by 3.28–5.46 percentage points across eight tasks.

By Chenyu Zhu, Ruoyu Zhao, Zhichao Lu
Hugging Face Trending Papers
Oct 9

Tabular Foundation Models Are Effectively Shallow

The study shows that tabular foundation models (TFMs) can be dramatically simplified without losing performance. By replacing up to 96% of transformer blocks with a label‑free affine translator, researchers found that half‑depth models still outperform full‑depth TFMs and tuned GBDTs across 171 classification datasets. The simplification reduces parameters by up to 1.5 B, speeds GPU inference up to 6×, and cuts memory usage by 6× with minimal impact on AUROC.

arXiv AI
Oct 12

Tabular Foundation Models Are Effectively Shallow

The paper shows that Tabular Foundation Models (TFMs) are highly overparameterized, with up to 96% of transformer blocks removable without significant loss in performance. Using a closed‑form, label‑free affine translator, the authors demonstrate that halving the depth of eight leading TFMs costs at most $0.002$ median AUROC, while a single‑block TabPFN‑3 remains competitive. Removing depth saves up to 1.5 B parameters, speeds GPU inference up to 6×, and reduces memory usage by 6× with negligible accuracy loss.

By Irene Cannistraci, Julia E. Vogt
arXiv Machine Learning
Sep 10

Dense Structural Compression of Transformers via Gauge-Correct Channel Removal

The paper introduces GaugeLasso, a method that applies symmetric group‑lasso penalties to transformer channels during training, enabling entire tensor slices to be zeroed out while maintaining dense tensors for GPU efficiency. By calibrating channel penalties based on inference utility per compute, the network self‑organizes into depth‑dependent structural profiles that can be dramatically smaller than the original architecture, achieving up to 255‑fold compression on a polynomial division task and outperforming hand‑designed baselines on language modeling and autoencoding benchmarks. The approach also accelerates training and reveals over‑provisioned axes that guide subsequent design iterations.

By Jed A. Duersch, Na\"im Es-Sebbani, Nathana\"el Haas, Zied Bouraoui
arXiv Machine Learning
Oct 15

Spectral-MoE: Heterogeneous Per-Layer Expert Utilization in Dense-to-MoE Conversion

Spectral-MoE introduces a method for allocating heterogeneous per-layer expert utilization in dense-to-mixture-of-experts (MoE) conversion of large language models. It offers both static and dynamic allocators that learn to distribute a utilization budget across layers, improving performance over uniform allocation in both analytic- and learning-based conversion baselines. Experiments on Llama-2-7B, Llama-3-8B, and Qwen2.5-7B show significant reductions in perplexity and accuracy gains at various FFN utilizations.

By Zachary Broveak, Christian Kubicka, Thierry Tambe
arXiv Machine Learning
Sep 11

LILA: Calibration-Free Structured Pruning of Large Language Models via Latent Spectral Geometry

LILA (Latent-Informed Layer Analysis) introduces a calibration‑free method for structured pruning of large language models by scoring neuron importance using the Kolmogorov–Smirnov distance between singular value distributions of full and neuron‑ablated feed‑forward network weight matrices. The approach requires no training, calibration data, or auxiliary networks, and outperforms existing methods such as PruneNet and SliceGPT on LLaMA‑2‑7B and Phi‑2 at various sparsity levels. After a single epoch of LoRA fine‑tuning, LILA matches heavily calibrated baselines, and a Neural Tangent Kernel analysis provides theoretical support for its spectral importance criterion. Additionally, LILA can dynamically allocate sparsity budgets, achieving state‑of‑the‑art generative preservation and revealing architectural bottlenecks at higher compression.

By Sankar Behera, Dhruv Singh, Anshika Agnihotri, Raj Kumar Choudhary, Satyadev Ahlawat, Yamuna Prasad
arXiv Computation and Language
Oct 1

Learning Functional Subspaces for Neural Network Compression

arXiv:2609.40127v1 Announce Type: cross Abstract: Modern transformers pair impressive capabilities with substantial memory and compute demands. Low-rank weight factorization reduces both while keepin...

By Massimo Bini, Anders Christensen, Stephan Alaniz, Judah Goldfeder, Ole Winther, Yann LeCun, Ravid Shwartz-Ziv, Zeynep Akata
arXiv AI
Oct 27

Fantastic Pretraining Optimizers and Where to Find Them

The paper evaluates ten deep learning optimizers across models ranging from 0.1B to 1.2B parameters and varying data-to-model ratios, highlighting that fair comparisons require rigorous hyperparameter tuning and end-of-training evaluations. It finds that claimed speedups over AdamW are lower than advertised, dropping to only 1.1× for the largest models, and that intermediate checkpoint comparisons can mislead due to learning‑rate decay. The study shows that matrix‑based optimizers like Muon and Soap achieve the highest speedups, but these benefits diminish as model size increases.

By Kaiyue Wen, David Hall, Tengyu Ma, Percy Liang
arXiv Machine Learning
Oct 28

BellowsKV: One Latent for Many Layers, Expanded on Demand

BellowsKV introduces a training‑free approach that maps the hidden states of multiple adjacent layers in a large language model to a single shared latent representation per token, allowing each layer to retrieve its own keys and values via a layer‑specific projection. The method retains the latent at full dimension and offers two compression strategies: BellowsKV‑Quant, which stores the latent at low precision, and BellowsKV‑Evict, which makes a shared eviction decision per block. Experiments on Llama‑3.1‑8B, Mistral‑7B, and Qwen2.5‑7B show that BellowsKV‑Quant preserves about 99% of full‑cache accuracy at 3.6× compression and 97‑98% at 13‑14×, outperforming existing cross‑layer methods that drop to at most 84% accuracy at 16× compression.

By Jiamu Zhang, Hanjie Chen