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.
arXiv:2610.02559v1 Announce Type: new Abstract: As neural networks continue to grow in scale, model compression is becoming increasingly important for efficient inference under limited computational...
arXiv:2606. 01402v1 Announce Type: cross Abstract: Neural network compression is commonly achieved by pruning parameters based on local importance scores, e.
arXiv:2603. 02234v3 Announce Type: replace-cross Abstract: The Strong Lottery Ticket Hypothesis (SLTH) states that large, randomly initialized neural networks contain sparse subnetworks capable of approximating a target function at initialization without training, suggesting that pruning alone is sufficient.
arXiv:2608. 06766v1 Announce Type: cross Abstract: Training changes a network's predictions while allocating task-relevant structure across its internal units.
arXiv:2609.24401v1 Announce Type: new Abstract: Structured pruning is a model compression technique that is used to reduce the computational cost of deploying deep neural networks on resource-constra...
arXiv:2609.26167v1 Announce Type: new Abstract: Activation-energy pruning -- removing weights whose product of magnitude and cumulative pre-synaptic spike count falls below a threshold -- was establi...
arXiv:2607. 26940v1 Announce Type: new Abstract: Ensembles are a standard way to improve the performance and robustness of deep neural networks, but their effectiveness crucially depends on both the quality and the diversity of individual models.
arXiv:2607. 18930v1 Announce Type: cross Abstract: The Universal Approximation Theorem states that a neural network with a single hidden layer is sufficient to approximate any continuous univariate function on a compact domain to arbitrary error.
Ensembles are a standard way to improve the performance and robustness of deep neural networks, but their effectiveness crucially depends on both the quality and the diversity of individual models. Most neural architecture search (NAS) methods are computationally expensive.
arXiv:2606. 01666v1 Announce Type: cross Abstract: The scaling of Large Language Models (LLMs) has driven significant performance gains but created substantial challenges in inference efficiency.
The Universal Approximation Theorem states that a neural network with a single hidden layer is sufficient to approximate any continuous univariate function on a compact domain to arbitrary error. However, the uniqueness of such neural network representations is not guaranteed, raising questions about practical identifiability.
arXiv:2602. 24266v2 Announce Type: replace-cross Abstract: Which internal mechanisms of a neural network can be replaced while preserving the computation it performs?