Deep Learning

SRNNs reveal behaviorally-relevant neural dynamics switches!

TPNet boosts temporal link prediction accuracy and efficiency by unifying relative encodings via temporal walk matrices and using random feature propagation.

Boosting Neural ODE training, Temporal Adaptive Batch Normalization (TA-BN) resolves traditional Batch Normalization’s limitations by providing a continuous-time counterpart, enabling deeper networks …

Boosting neural network surface processing: Using principal curvatures as input significantly improves segmentation and classification accuracy while reducing computational overhead.

IRE framework expedites the discovery of flat minima in deep learning, enhancing generalization and convergence. By decoupling the dynamics of flat and sharp directions, IRE boosts sharpness reduction…

Boost equivariant model training by strategically relaxing constraints during training, enhancing optimization and generalization!

Constrained Parameter Regularization (CPR) outperforms traditional weight decay by dynamically adapting regularization strengths for individual parameters, leading to better deep learning model perfor…

Training high-quality diffusion models efficiently is now possible, thanks to novel sample complexity bounds improving exponentially on previous work.

Researchers enhanced diffusion samplers by developing a novel exploration strategy and a unified library, improving sample quality and addressing reproducibility challenges.

PropEn: a novel framework for implicitly guided design optimization that leverages ‘matching’ to boost efficiency by matching samples and approximating the gradient without a discriminator.

HyperLogic uses hypernetworks to generate diverse, accurate, and concise rule sets from neural networks, enhancing both interpretability and accuracy in rule learning.

Hyper-opinion Evidential Deep Learning (HEDL) enhances out-of-distribution detection by integrating sharp and vague evidence for superior uncertainty estimation and classification accuracy.

Deep network pruning’s fundamental limits are characterized, revealing how weight magnitude and network sharpness determine the maximum achievable sparsity.

Boost ensemble accuracy by predicting performance with fewer classifiers using a novel polarization law and refined error bounds.

HORSE: A novel attention-based neural network significantly improves large-scale neural subset selection by up to 20%, addressing limitations in existing methods.

Higher-rank irreducible Cartesian tensors boost accuracy and efficiency in equivariant message-passing neural networks for atomistic simulations.

Hierarchical Hybrid Sliced Wasserstein (H2SW) solves the challenge of comparing complex, heterogeneous joint distributions by introducing novel slicing operators, leading to a scalable and statistical…

HHD-GP leverages Helmholtz-Hodge decomposition within Gaussian Processes to learn physically meaningful components of dynamical systems, enhancing prediction accuracy and interpretability.

HEPrune accelerates private deep learning training 16x by integrating encrypted data pruning, achieving this speedup with minimal accuracy loss.

Hamiltonian Monte Carlo struggles with ReLU neural networks: high rejection rates hinder Bayesian deep learning.