Multi-Task Learning with Covariate-Overlap Regularization
stat.ML, cs.LG, stat.ME
Submitted: 2025-05-30
Updated: 2026-09-05
Code: https://github.com/kw2934/ARMUL
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- BAM! Born-Again Multi-Task Networks for Natural Language Understanding
- Multi-Task Learning with Deep Neural Networks: A Survey
- Few-Shot Learning via Learning the Representation, Provably
- Adapting Auxiliary Losses Using Gradient Similarity
- Parameter-Efficient Fine-Tuning for Large Models: A Comprehensive Survey
- Representation Transfer Learning for Semiparametric Regression
- Adam: A Method for Stochastic Optimization
- Improving Multi-Task Deep Neural Networks via Knowledge Distillation for Natural Language Understanding
- Exploring the Complexity of Deep Neural Networks through Functional Equivalence
- Learning from Similar Linear Representations: Adaptivity, Minimaxity, and Robustness
- Trace Norm Regularised Deep Multi-Task Learning
- Hyper-Parameter Optimization: A Review of Algorithms and Applications
- Covariate-Elaborated Robust Partial Information Transfer with Conditional Spike-and-Slab Prior
Related papers
- Behavior of prediction performance metrics with rare events
- Optimal Estimation of Generic Dynamics by Path-Dependent Neural Jump ODEs
- A Posterior-Dynamics Framework for Imaging Inverse Problems with Pretrained Diffusion Priors
- One Permutation Is All You Need: Fast, Deterministic Feature Importance and Model Stress-Testing
- Online Conformal Prediction for Non-Exchangeable Panel Data
- Deep Time-Series Forecasting in 10 Years: A Survey