Statistical Learning
Energy Discrepancies: A Score-Independent Loss for Energy-Based Models
We propose a novel loss function called Energy Discrepancy (ED) which does not rely on the computation of scores or expensive Markov chain Monte Carlo.
Facilitating Multimodal Classification via Dynamically Learning Modality Gap Y ang
Multimodal learning falls into the trap of the optimization dilemma due to the modality imbalance phenomenon, leading to unsatisfactory performance in real applications.
On the Gini-impurity Preservation For Privacy Random Forests
This work takes one step towards data encryption by incorporating some crucial ingredients of learning algorithm.
Adaptive Contextual Perception: How to Generalize to New Backgrounds and Ambiguous Objects
Motivated by our analysis results, we propose new data augmentation methods aimed at enhancing model generalization.
Robust Gaussian Processes via Relevance Pursuit
We compare the model's performance relative to other approaches on diverse regression and Bayesian optimization tasks, including the challenging but common
On Sampling Strategies for Spectral Model Sharding
The general recipe for each communication round is composed of three steps.