arXiv Machine Learning
Annealed correlation and quenched noise sensitivity in biased deep neural networks
Read the original on arXiv Machine Learning →The Flow has not summarised this story yet — read it at arXiv Machine Learning.
Related stories
arXiv AI
Jul 1
A Coherence Law for Trainability in Noisy Equivariant Quantum Neural Networks
arXiv:2606. 30688v1 Announce Type: cross Abstract: Symmetry provides a quantum neural network structure, but on its own it does not keep the network trainable once noise is present.
arXiv Machine Learning
Aug 28
High Probability Derivative Bounds for Random tanh Neural Networks on a Hypercube
The paper establishes high‑probability bounds on mixed input derivatives for wide random neural networks whose activation derivatives grow factorially, with a focus on anh networks initialized with Xavier weights. For scalar‑output anh networks with Gaussian weights, the authors prove that when the hidden width exceeds a depth‑dependent threshold, the derivative of any order satisfies a bound that is independent of depth for first‑order derivatives and grows at most polynomially with depth for higher‑order mixed derivatives. These results yield high‑probability estimates for the Euclidean Lipschitz constant and weighted Sobolev norms, linking the regularity of network realizations to quasi‑Monte Carlo integration and its potential impact on QMC‑based training.
arXiv Machine Learning
Sep 16
Bias-Induced Crossover in Absolute Capacity of Dense Associative Memory
arXiv:2609. 17477v1 Announce Type: cross Abstract: The absolute capacity of dense associative memory has mainly been analyzed for unbiased patterns.
arXiv Machine Learning
Jul 17
Random Parameter Noise Does Not Make Exact ReLU Verification Easy
arXiv:2607. 14375v1 Announce Type: cross Abstract: We study exact verification of ReLU networks in an adversarial smoothed model.
arXiv AI
Oct 15
When Does Compensating Inherited Quantization Error Help? Mean-Square Guarantees for Layer-Wise Quantization and Their Limits
arXiv:2610.16020v1 Announce Type: cross Abstract: Layer-wise post-training quantization methods let each layer compensate for the quantization error inherited from earlier layers. We ask under what a...
arXiv Machine Learning
Jul 15
Same Loss, Same Noise, Opposite Schedules: Noise Structure and Optimizer Normalization Jointly Determine Whether Learning-Rate Cooldown Helps
arXiv:2607. 12360v1 Announce Type: new Abstract: The cooldown phase of a warmup-stable-decay (WSD) learning-rate schedule, now a default in large-model pretraining, lowers the final training loss in some settings and does nothing in others.