More Like this

1. COMPARING COLLABORATIVE LEARNING IN VARIOUS LEARNING MODALITIES

   https://doi.org/10.35490/EC3.2023.306  

   Suwal, Ashma; Wu, Wei; Luo, Yupeng (July 2023, Computing in Construction)
2. Direction Concentration Learning: Enhancing Congruency in Machine Learning

   https://doi.org/10.1109/TPAMI.2019.2963387  

   Luo, Yan; Wong, Yongkang; Kankanhalli, Mohan; Zhao, Qi (December 2019, IEEE Transactions on Pattern Analysis and Machine Intelligence)
3. Desynchronous learning in a physics-driven learning network

   https://doi.org/10.1063/5.0084631  

   Wycoff, J. F.; Dillavou, S.; Stern, M.; Liu, A. J.; Durian, D. J. (April 2022, The Journal of Chemical Physics)

   In a neuron network, synapses update individually using local information, allowing for entirely decentralized learning. In contrast, elements in an artificial neural network are typically updated simultaneously using a central processor. Here, we investigate the feasibility and effect of desynchronous learning in a recently introduced decentralized, physics-driven learning network. We show that desynchronizing the learning process does not degrade the performance for a variety of tasks in an idealized simulation. In experiment, desynchronization actually improves the performance by allowing the system to better explore the discretized state space of solutions. We draw an analogy between desynchronization and mini-batching in stochastic gradient descent and show that they have similar effects on the learning process. Desynchronizing the learning process establishes physics-driven learning networks as truly fully distributed learning machines, promoting better performance and scalability in deployment. 

   more » « less
4. Transfer Learning in Deep Reinforcement Learning: A Survey

   https://doi.org/10.1109/TPAMI.2023.3292075  

   Zhu, Zhuangdi; Lin, Kaixiang; Jain, Anil K; Zhou, Jiayu (November 2023, IEEE Transactions on Pattern Analysis and Machine Intelligence)
5. Learning to Generalize Provably in Learning to Optimize

   Yang, Junjie; Chen, Tianlong; Zhu, Mingkang; He, Fengxiang; Tao, Dacheng; Liang, Yingbin; Wang, Zhangyang (April 2023, International Conference on Artificial Intelligence and Statistics)

   Learning to optimize (L2O) has gained increasing popularity, which automates the design of optimizers by data-driven approaches. However, current L2O methods often suffer from poor generalization performance in at least two folds: (i) applying the L2O-learned optimizer to unseen optimizees, in terms of lowering their loss function values (optimizer generalization, or “generalizable learning of optimizers”); and (ii) the test performance of an optimizee (itself as a machine learning model), trained by the optimizer, in terms of the accuracy over unseen data (optimizee generalization, or “learning to generalize”). While the optimizer generalization has been recently studied, the optimizee generalization (or learning to generalize) has not been rigorously studied in the L2O context, which is the aim of this paper. We first theoretically establish an implicit connection between the local entropy and the Hessian, and hence unify their roles in the handcrafted design of generalizable optimizers as equivalent metrics of the landscape flatness of loss functions. We then propose to incorporate these two metrics as flatness-aware regularizers into the L2O framework in order to meta-train optimizers to learn to generalize, and theoretically show that such generalization ability can be learned during the L2O meta-training process and then transformed to the optimizee loss function. Extensive experiments consistently validate the effectiveness of our proposals with substantially improved generalization on multiple sophisticated L2O models and diverse optimizees. 

   more » « less