Natural Mitigation of Catastrophic Interference: Continual Learning in Power-Law Learning Environmentsby Atith Gandhi, Raj Sanjay…
LDReg: Local Dimensionality Regularized Self-Supervised Learningby Hanxun Huang, Ricardo J. G. B. Campello, Sarah Monazam…
SymbolNet: Neural Symbolic Regression with Adaptive Dynamic Pruning for Compressionby Ho Fung Tsoi, Vladimir Loncar,…
Offline Imitation Learning by Controlling the Effective Planning Horizonby Hee-Jun Ahn, Seong-Woong Shim, Byung-Jun LeeFirst…
An Optimal Transport Approach for Computing Adversarial Training Lower Bounds in Multiclass Classificationby Nicolas Garcia…
CEL: A Continual Learning Model for Disease Outbreak Prediction by Leveraging Domain Adaptation via Elastic…
Decoupled Prototype Learning for Reliable Test-Time Adaptationby Guowei Wang, Changxing Ding, Wentao Tan, Mingkui TanFirst…
REValueD: Regularised Ensemble Value-Decomposition for Factorisable Markov Decision Processesby David Ireland, Giovanni MontanaFirst submitted to…
Stochastic Subnetwork Annealing: A Regularization Technique for Fine Tuning Pruned Subnetworksby Tim Whitaker, Darrell WhitleyFirst…
Efficient Frameworks for Generalized Low-Rank Matrix Bandit Problemsby Yue Kang, Cho-Jui Hsieh, Thomas C. M.…