Deep Learning
Missing Data Imputation and Acquisition with Deep Hierarchical Models and Hamiltonian Monte Carlo
In the literature, the issue of model flexibility and inference bias are often addressed separately.
Missing Data Imputation and Acquisition with Deep Hierarchical Models and Hamiltonian Monte Carlo
In the literature, the issue of model flexibility and inference bias are often addressed separately.
Fast Neural Kernel Embeddings for General Activations
Moreover, most prior works on neural kernels have focused on the ReLU activation, mainly due to its popularity but also due to the difficulty of computing such kernels for general activations.
MoCapAct: A Multi-Task Dataset for Simulated Humanoid Control Nolan Wagener
Simulated humanoids are an appealing research domain due to their physical capabilities. Nonetheless, they are also challenging to control, as a policy must drive an unstable, discontinuous, and high-dimensional physical system.
Multitasking Models are Robust to Structural Failure: A Neural Model for Bilingual Cognitive Reserve
We find a surprising connection between multitask learning and robustness to neuron failures.
AutoMTL: A Programming Framework for Automating Efficient Multi-Task Learning
The effective adoption of MTL faces two main challenges.