Recent work on automated data augmentation strategies has led to state-of-the-art results in image classification and object detection. An obstacle to a large-scale adoption of these methods is that they require a separate and expensive search phase. A common way to overcome the expense of the search phase was to use a smaller proxy task.

By doing so, our method SST enjoys significant superiority over the benchmark UCF101 and HMDB51 datasets.

In this work, we ask two key questions. First, in a more realistic setting where only a CPU is available, is the GNN model still competitive?

Many problems in machine learning reduce to learning a probability distribution (or policy) over sequences of discrete actions so as to maximize a downstream utility function. Examples include generating text sequences to maximize a task-specific metric like BLEU and generating action sequences in reinforcement learning (RL) to maximize expected return.

Thank you for the thoughtful and careful reviews. We hope the AC nominates some of you for reviewer awards. There should be a baseline using MCTS and assuming access to simulator / common random numbers. There appears to be some imprecision in reviews about what this means. Then environment stochasticity is re-sampled and the algorithm repeats.

After each decision to choose a particular arm, the learner receives some form of feedback - typically a numerical reward - determined by a feedback mechanism of the chosen arm.

Computing the gradient of model hyperparameters, i.e., hypergradient, enables a