Statistical Learning
FedGTST: Boosting Global Transferability of Federated Models via Statistics Tuning
In addition to boosting the performance of a target domain model, TL also reduces the computational cost of fine-tuning the target domain model.
Gated Inference Network: Inference and Learning State-Space Models
This paper advances temporal reasoning within dynamically changing high-dimensional noisy observations, focusing on a latent space that characterizes the nonlinear dynamics of objects in their environment.
Learning Multimodal Behaviors from Scratch with Diffusion Policy Gradient Zechu Li
Meanwhile, diffusion models emerged as a powerful framework for multimodal learning.
43c6d9b0d11696f89c75157919a0334a-Paper-Conference.pdf
Calibration is a well-studied property of predictors which guarantees meaningful uncertainty estimates.
A Bayesian Approach to Data Point Selection
Thus, we propose a novel Bayesian approach to DPS.
Soft ascent-descent as a stable and flexible alternative to flooding Matthew J. Holland
While many such candidates are indeed essentially "optimal"