Technology
Hierarchical Reinforcement Learning for Zero-shot Generalization with Subtask Dependencies
Sungryull Sohn, Junhyuk Oh, Honglak Lee
Neural Information Processing Systems http://nips.cc/
Multi-ObjectiveDeepLearning withAdaptiveReferenceVectors
Many deep learning models involve optimizing multiple objectives. Since objectives are often conflicting, we aim to get diverse and representative trade-off solutions among these objectives.
Batch-Instance Normalization for Adaptively Style-Invariant Neural Networks
Neural Information Processing Systems http://nips.cc/
Towardsmodularandprogrammablearchitecture search
However, current systems focus on specific use-cases (e.g.
4ab50afd6dcc95fcba76d0fe04295632-AuthorFeedback.pdf
Our language also allowsustorepresent infinite search22 spaces, as substitutions are lazy and can create new hyperparameters and modules. Infinite search spaces are not23 possible with current hyperparameter optimization tools.
Communication trade-offs for Local-SGD with large step size
Aymeric Dieuleveut, Kumar Kshitij Patel
Neural Information Processing Systems http://nips.cc/