Reward Model Learning vs. Direct Policy Optimization: A Comparative Analysis of Learning from Human Preferencesby Andi…
Out-of-distribution robustness for multivariate analysis via causal regularisationby Homer Durand, Gherardo Varando, Nathan Mankovich, Gustau…
A Regularization-based Transfer Learning Method for Information Extraction via Instructed Graph Decoderby Kedi Chen, Jie…
Overestimation, Overfitting, and Plasticity in Actor-Critic: the Bitter Lesson of Reinforcement Learningby Michal Nauman, Michał…
Rethinking Multi-domain Generalization with A General Learning Objectiveby Zhaorui Tan, Xi Yang, Kaizhu HuangFirst submitted…
Analyzing and Reducing Catastrophic Forgetting in Parameter Efficient Tuningby Weijieying Ren, Xinlong Li, Lei Wang,…
Catastrophic Overfitting: A Potential Blessing in Disguiseby Mengnan Zhao, Lihe Zhang, Yuqiu Kong, Baocai YinFirst…
FedUV: Uniformity and Variance for Heterogeneous Federated Learningby Ha Min Son, Moon-Hyun Kim, Tai-Myoung Chung,…
On the Inductive Biases of Demographic Parity-based Fair Learning Algorithmsby Haoyu Lei, Amin Gohari, Farzan…
Autoencoder-based General Purpose Representation Learning for Customer Embeddingby Jan Henrik Bertrand, David B. Hoffmann, Jacopo…