Traversing Pareto Optimal Policies: Provably Efficient Multi-Objective Reinforcement Learningby Shuang Qiu, Dake Zhang, Rui Yang,…
Generalization Bounds of Surrogate Policies for Combinatorial Optimization Problemsby Pierre-Cyril Aubin-Frankowski, Yohann De Castro, Axel…
Take a Step and Reconsider: Sequence Decoding for Self-Improved Neural Combinatorial Optimizationby Jonathan Pirnay, Dominik…
Enhanced Feature Learning via Regularisation: Integrating Neural Networks and Kernel Methodsby Bertille Follain, Francis BachFirst…
Gradient-based inference of abstract task representations for generalization in neural networksby Ali Hummos, Felipe del…
In Search for Architectures and Loss Functions in Multi-Objective Reinforcement Learningby Mikhail Terekhov, Caglar GulcehreFirst…
Federated Automatic Latent Variable Selection in Multi-output Gaussian Processesby Jingyi Gao, Seokhyun ChungFirst submitted to…
Adaptive Gradient Regularization: A Faster and Generalizable Optimization Technique for Deep Neural Networksby Huixiu Jiang,…
Stochastic Variance-Reduced Iterative Hard Thresholding in Graph Sparsity Optimizationby Derek Fox, Samuel Hernandez, Qianqian TongFirst…
Functional Acceleration for Policy Mirror Descentby Veronica Chelu, Doina PrecupFirst submitted to arxiv on: 23…