The RL image classification environment consists of a dataset of labelled images. For the variant labelled "Adaptive", we train a classifier In this section, we will derive the optimal memoryless policy. M: it receives the highest expected test-time return amongst all possible policies. This proposition follows directly from the definition of the epistemic POMDP . In both MDPs, the reward for the "stay" action is always zero.

The data used during training in any given application space is directly tied to the performance of the system once deployed. While there are many other factors that go into producing high performance models within machine learning, there is no doubt that the data used to train a system provides the foundation from which to build. One of the underlying rule of thumb heuristics used within the machine learning space is that more data leads to better models, but there is no easy answer for the question, "How much data is needed?" This work examines a modulation classification problem in the Radio Frequency domain space, attempting to answer the question of how much training data is required to achieve a desired level of performance, but the procedure readily applies to classification problems across modalities. The ultimate goal is determining an approach that requires the least amount of data collection to better inform a more thorough collection effort to achieve the desired performance metric. While this approach will require an initial dataset that is germane to the problem space to act as a \textit{target} dataset on which metrics are extracted, the goal is to allow for the initial data to be orders of magnitude smaller than what is required for delivering a system that achieves the desired performance. An additional benefit of the techniques presented here is that the quality of different datasets can be numerically evaluated and tied together with the quantity of data, and ultimately, the performance of the architecture in the problem domain.

This paper is concerned with ranking many pre-trained deep neural networks (DNNs), called checkpoints, for the transfer learning to a downstream task. Thanks to the broad use of DNNs, we may easily collect hundreds of checkpoints from various sources. Which of them transfers the best to our downstream task of interest? Striving to answer this question thoroughly, we establish a neural checkpoint ranking benchmark (NeuCRaB) and study some intuitive ranking measures. These measures are generic, applying to the checkpoints of different output types without knowing how the checkpoints are pre-trained on which dataset. They also incur low computation cost, making them practically meaningful. Our results suggest that the linear separability of the features extracted by the checkpoints is a strong indicator of transferability. We also arrive at a new ranking measure, NLEEP, which gives rise to the best performance in the experiments.

Generalization is a central challenge for the deployment of reinforcement learning (RL) systems in the real world. In this paper, we show that the sequential structure of the RL problem necessitates new approaches to generalization beyond the well-studied techniques used in supervised learning. While supervised learning methods can generalize effectively without explicitly accounting for epistemic uncertainty, we show that, perhaps surprisingly, this is not the case in RL. We show that generalization to unseen test conditions from a limited number of training conditions induces implicit partial observability, effectively turning even fully-observed MDPs into POMDPs. Informed by this observation, we recast the problem of generalization in RL as solving the induced partially observed Markov decision process, which we call the epistemic POMDP. We demonstrate the failure modes of algorithms that do not appropriately handle this partial observability, and suggest a simple ensemble-based technique for approximately solving the partially observed problem. Empirically, we demonstrate that our simple algorithm derived from the epistemic POMDP achieves significant gains in generalization over current methods on the Procgen benchmark suite.

Summary: Transfer Learning (TL) may be the most important aid to adoption of deep learning in the last several years. This new LEEP measure predicts the accuracy of the transfer and should make TL faster, cheaper, and better. What is the single most important innovation in deep learning in the last several years? There might be several candidates. You might argue for tensorflow specific chips, or BERT architecture for improving NLP.

We introduce a new measure to evaluate the transferability of representations learned by classifiers. Our measure, the Log Expected Empirical Prediction (LEEP), is simple and easy to compute: when given a classifier trained on a source data set, it only requires running the target data set through this classifier once. We analyze the properties of LEEP theoretically and demonstrate its effectiveness empirically. Our analysis shows that LEEP can predict the performance and convergence speed of both transfer and meta-transfer learning methods, even for small or imbalanced data. Moreover, LEEP outperforms recently proposed transferability measures such as negative conditional entropy and H scores. Notably, when transferring from ImageNet to CIFAR100, LEEP can achieve up to 30% improvement compared to the best competing method in terms of the correlations with actual transfer accuracy.