arXiv:2608. 06177v1 Announce Type: new Abstract: Binary neural networks are very attractive for constrained deployment, enabling small footprint and low-power inference.
arXiv:2606. 27759v1 Announce Type: new Abstract: Training binary neural networks (BNNs) from scratch is dominated by the straight-through estimator (STE), whose forward/backward mismatch produces severe accuracy degradation as networks deepen.
arXiv:2606. 05863v1 Announce Type: new Abstract: Grokking suggests that fitting the training data and learning a simple underlying rule may occur on different time scales.
arXiv:2607. 23777v1 Announce Type: cross Abstract: The discovery of scaling laws has motivated training neural networks on ever increasing quantities of data.
arXiv:2607. 20552v1 Announce Type: new Abstract: Grokking -- the delayed generalization of neural networks long after they have memorized their training data -- wastes thousands of training epochs and is notoriously unpredictable.
arXiv:2511. 04981v2 Announce Type: replace Abstract: Model depth is a double-edged sword in deep learning: deeper models achieve higher accuracy but require higher computational cost.
arXiv:2604. 00230v2 Announce Type: replace Abstract: Neural collapse (NC) -- the convergence of penultimate-layer features to a simplex equiangular tight frame -- is well understood at equilibrium, but the dynamics governing its onset remain poorly characterised.
arXiv:2606. 25256v1 Announce Type: cross Abstract: We introduce Pre-Warm, a simple yet effective zero-training-cost method for data-conditioned initialization of the first convolutional layer.
arXiv:2605. 15435v2 Announce Type: replace Abstract: Standard deep-learning pipelines usually choose the network architecture before training and keep it fixed throughout optimization.
arXiv:2607. 14427v1 Announce Type: new Abstract: A depth-recurrent transformer applies a weight-tied core a variable number of times, and prior work has shown that training with a randomized recursion count yields one checkpoint usable across a range of inference depths.
arXiv:2606. 12278v1 Announce Type: cross Abstract: Neural network pruning reduces model size by removing less important parameters while aiming to preserve predictive performance.
arXiv:2510. 04500v3 Announce Type: replace Abstract: This work demonstrates how increasing the number of neurons in a network without increasing its total number of non-zero parameters improves performance.
arXiv:2505. 22578v2 Announce Type: replace Abstract: The optimization of neural networks under weight decay remains poorly understood from a theoretical standpoint.