arXiv:2607. 16761v1 Announce Type: cross Abstract: Dropout and Random Gradient Masking (RaM) are two training techniques used to improve performance in deep learning.
arXiv:2507. 09029v5 Announce Type: replace-cross Abstract: Pre-training large neural networks at scale imposes heavy memory demands on accelerators and often requires costly communication.
arXiv:2106. 06998v5 Announce Type: replace Abstract: Training convolutional neural networks at scale demands substantial memory, largely because intermediate activations must be stored for backpropagation.
arXiv:2606. 06772v1 Announce Type: cross Abstract: Understanding the generalization performance of over-parameterized neural networks has become a central topic in deep learning theory.
arXiv:2402.11215v4 Announce Type: replace Abstract: The choice of batch size in minibatch stochastic gradient optimization is critical for both optimization and generalization performance in large-sc...
The paper demonstrates that layer dropout, also known as stochastic depth, can be effectively used in state‑of‑the‑art large language model (LLM) training. By optimizing the layer distribution, schedule, and optimizer settings, the authors show that layer dropout can reduce training loss while saving up to 25 % of training FLOPs. Additionally, layer dropout enables post‑training optimizations such as early exit and self‑speculative decoding, achieving up to 1.5× inference speedup with negligible accuracy loss across models ranging from 271 M to 8.2 B parameters and datasets up to 160 B tokens.
arXiv:2512. 13853v2 Announce Type: replace Abstract: In this work, we investigate the existence and effect of percolation in training deep Neural Networks (NNs) with dropout.
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. 06772v2 Announce Type: replace-cross Abstract: Characterizing the optimization dynamics and statistical performance of over-parameterized deep neural networks (DNNs) remains a central challenge in understanding the remarkable success of deep learning.
arXiv:2610. 01578v1 Announce Type: new Abstract: Why can masked prediction learn useful representations that unmasked reconstruction misses?
arXiv:2508. 09697v4 Announce Type: replace Abstract: Noisy labels are inevitable in real-world multimedia applications.
arXiv:2510. 02779v4 Announce Type: replace Abstract: Recent advances have significantly improved our understanding of the generalization performance of gradient descent (GD) methods in deep neural networks.
arXiv:2606. 06764v1 Announce Type: cross Abstract: Recent progress has been made in understanding the statistical generalization performance of gradient descent methods for overparameterized neural networks within the neural tangent kernel (NTK) regime.