Search Results for author:
Found 8 papers, 3 papers with code
Enhancing Transfer Learning with Flexible Nonparametric Posterior Sampling
The nonparametric learning (NPL) method is a recent approach that employs a nonparametric prior for posterior sampling, efficiently accounting for model misspecification scenarios, which is suitable for transfer learning scenarios that may involve the distribution shift between upstream and downstream tasks.
Joint-Embedding Masked Autoencoder for Self-supervised Learning of Dynamic Functional Connectivity from the Human Brain
Although generative self-supervised learning techniques, especially masked autoencoders, have shown promising results in representation learning in various domains, their application to dynamic graphs for dynamic functional connectivity remains underexplored, facing challenges in capturing high-level semantic representations.
Traversing Between Modes in Function Space for Fast Ensembling
While this provides a way to efficiently train ensembles, for inference, multiple forward passes should still be executed using all the ensemble parameters, which often becomes a serious bottleneck for real-world deployment.
Regularizing Towards Soft Equivariance Under Mixed Symmetries
The key component of our method is what we call equivariance regularizer for a given type of symmetries, which measures how much a model is equivariant with respect to the symmetries of the type.
SWAMP: Sparse Weight Averaging with Multiple Particles for Iterative Magnitude Pruning
Given the ever-increasing size of modern neural networks, the significance of sparse architectures has surged due to their accelerated inference speeds and minimal memory demands.
Martingale Posterior Neural Processes
Based on this result, instead of assuming any form of the latent variables, we equip a NP with a predictive distribution implicitly defined with neural networks and use the corresponding martingale posteriors as the source of uncertainty.
Improving Ensemble Distillation With Weight Averaging and Diversifying Perturbation
Ensembles of deep neural networks have demonstrated superior performance, but their heavy computational cost hinders applying them for resource-limited environments.
Scale Mixtures of Neural Network Gaussian Processes
We show that simply introducing a scale prior on the last-layer parameters can turn infinitely-wide neural networks of any architecture into a richer class of stochastic processes.
