arXiv AI
Jun 2
Neural Network Compression by Approximate Differential Equivalence
arXiv:2606. 01402v1 Announce Type: cross Abstract: Neural network compression is commonly achieved by pruning parameters based on local importance scores, e.
Neuron merging via inverse-activation regression for post-training compression of sigmoid neural networks
Related stories
arXiv AI
Jul 24
Hilbert Operator for Progressive Encoding (HOPE): A Mathematical Framework for Deconstructing Learned Representations in Deep Networks
arXiv:2607. 21366v1 Announce Type: cross Abstract: Deep neural networks encode complex representations, but deconstructing this internal knowledge remains a challenge.
arXiv Machine Learning
Sep 7
From Deep to Shallow: Unconstrained and Efficient Layer Merging Strategy
The paper proposes a new strategy for merging layers in deep neural networks, enabling depth compression without requiring an analytical solution for convolutions with padding and without increasing kernel size. This approach addresses limitations of previous methods that struggled with padded convolutions and larger kernels, and it is validated across various architectures and datasets with measured inference speed-ups on embedded platforms.
arXiv Machine Learning
Jul 22
Partial Fusion of Neural Networks: Efficient Tradeoffs Between Ensembles and Weight Aggregation
arXiv:2605. 22350v2 Announce Type: replace Abstract: Ensembles of neural networks typically outperform individual networks but incur large computational costs, whereas weight aggregation produces less costly, yet also less accurate, aggregate models.
Hugging Face Trending Papers
Jun 22
Hybrid Compression: Integrating Pruning and Quantization for Optimized Neural Networks
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.
arXiv Machine Learning
Jun 10
TENP: Trapezoidal Expert Neuron Pruning For Mixture-of-Experts
arXiv:2606. 09885v1 Announce Type: new Abstract: 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.
arXiv Machine Learning
Oct 3
CrossGMN: Graph Metanetworks for Cross-Architecture Weight-Space Transformations
CrossGMN introduces a graph metanetwork that processes a trained source network and an initialized target network simultaneously, enabling equivariant cross‑architecture weight‑space transformations. By preserving symmetry through cross‑network message passing, CrossGMN can refine target network initializations while remaining invariant to source permutations and equivariant to target permutations. Experiments demonstrate that CrossGMN accelerates knowledge distillation, transfers across datasets without retraining, and unifies compression from diverse source architectures into a common target architecture.
arXiv Machine Learning
Jun 24
Similarity of Neural Network Representations in Superposition
arXiv:2604. 00208v2 Announce Type: replace Abstract: Comparing internal representations is a central goal in neuroscience and machine learning, but standard linear alignment metrics (Representational Similarity Analysis, Centered Kernel Alignment, and linear regression) are frequently applied to neural activity coordinates rather than on the underlying features.
arXiv Machine Learning
Sep 21
Layerwise Decoupling for Stable Structured Sparsification of Fully Connected Layers
The paper introduces a layerwise, decoupled approach to structurally sparsify fully connected layers in pretrained neural networks. By extracting shallow two‑layer subnetworks, normalizing inner weights, and applying a structured group penalty to each block’s outer weight matrix, the method prunes neurons sequentially and reduces layer widths. The authors prove equivalence to a joint penalty for positively homogeneous activations, and demonstrate that this decoupled formulation is more robust, offering a broader regularization range and lower catastrophic over‑pruning while preserving accuracy in classification, sparse‑recovery, PINN, and OPT‑1.3B experiments.
arXiv AI
Jun 9
SmartMixed: A Two-Phase Training Strategy for Adaptive Activation Function Learning in Neural Networks
arXiv:2510. 22450v3 Announce Type: replace-cross Abstract: The choice of activation function plays a critical role in neural networks, yet most architectures still rely on fixed, uniform activation functions across all neurons.
arXiv Machine Learning
Sep 1
MOONSHOT : A Framework for Multi-Objective Pruning of Vision and Large Language Models
arXiv:2604.13287v2 Announce Type: replace Abstract: Weight pruning is a common technique for compressing large neural networks. We focus on the challenging post-training one-shot setting, where a pre...
arXiv AI
Sep 2
A Mathematical Theory of Reusable Neural Bases for Network Compression
The paper introduces the Linear Reusable Neural Bases Architecture (LRNBA), a framework that represents each network block as a linear combination of shared neural bases to improve parameter efficiency and reduce memory cost. Inspired by recurrent neural network designs, LRNBA enables the construction of wider and deeper networks within the same parameter budget. Experiments show that models using LRNBA converge as fast or faster than classical architectures, achieve lower loss, and maintain stable training dynamics.