Sample-efficient exploration is crucial not only for discovering rewarding experiences but also for adapting to environment changes in a task-agnostic fashion. A principled treatment of the problem of optimal input synthesis for system identification is provided within the framework of sequential Bayesian experimental design. In this paper, we present an effective trajectory-optimization-based approximate solution of this otherwise intractable problem that models optimal exploration in an unknown Markov decision process (MDP). By interleaving episodic exploration with Bayesian nonlinear system identification, our algorithm takes advantage of the inductive bias to explore in a directed manner, without assuming prior knowledge of the MDP. Empirical evaluations indicate a clear advantage of the proposed algorithm in terms of the rate of convergence and the final model fidelity when compared to intrinsic-motivation-based algorithms employing exploration bonuses such as prediction error and information gain. Moreover, our method maintains a computational advantage over a recent model-based active exploration (MAX) algorithm, by focusing on the information gain along trajectories instead of seeking a global exploration policy. A reference implementation of our algorithm and the conducted experiments is publicly available.

Federated learning enables the creation of a powerful centralized model without compromising data privacy of multiple participants. While successful, it does not incorporate the case where each participant independently designs its own model. Due to intellectual property concerns and heterogeneous nature of tasks and data, this is a widespread requirement in applications of federated learning to areas such as health care and AI as a service. In this work, we use transfer learning and knowledge distillation to develop a universal framework that enables federated learning when each agent owns not only their private data, but also uniquely designed models. We test our framework on the MNIST/FEMNIST dataset and the CIFAR10/CIFAR100 dataset and observe fast improvement across all participating models. With 10 distinct participants, the final test accuracy of each model on average receives a 20% gain on top of what's possible without collaboration and is only a few percent lower than the performance each model would have obtained if all private datasets were pooled and made directly available for all participants.

I NFERRING DYNAMICAL SYSTEMS WITH LONG-RANGE DEPENDENCIES THROUGH LINE ATTRACTOR REGULARIZATIONDominik Schmidt 1*, Georgia Koppe 1*, Max Beutelspacher 1,2, Daniel Durstewitz 1,3 1 Department of Theoretical Neuroscience, Central Institute of Mental Health, Medical Faculty Mannheim, Heidelberg University, Mannheim, Germany 3 Faculty of Physics and Astronomy, Heidelberg University * These authors contributed equally contact: {dominik.schmidt,georgia.koppe,daniel.durstewitz} A BSTRACT V anilla RNN with ReLU activation have a simple structure that is amenable to systematic dynamical systems analysis and interpretation, but they suffer from the exploding vs. vanishing gradients problem. Recent attempts to retain this simplicity while alleviating the gradient problem are based on proper initialization schemes or orthogonality/unitary constraints on the RNN's recurrence matrix, which, however, comes with limitations to its expressive power with regards to dynamical systems phenomena like chaos or multi-stability. Here, we instead suggest a regularization scheme that pushes part of the RNN's latent subspace toward a line attractor configuration that enables long short-term memory and arbitrarily slow time scales. We show that our approach excels on a number of benchmarks like the sequential MNIST or multiplication problems, and enables reconstruction of dynamical systems which harbor widely different time scales. 1 I NTRODUCTION Theories of complex systems in biology and physics are often formulated in terms of sets of stochastic differential or difference equations, i.e. as stochastic dynamical systems (DS). A longstanding desire is to retrieve these generating dynamical equations directly from observed time series data (Kantz & Schreiber, 2004). However, vanilla RNN as often used in this context are well known for their problems in capturing long-term dependencies and slow time scales in the data (Hochreiter & Schmidhuber, 1997; Bengio et al., 1994).

In many real-world applications of Machine Learning it is of paramount importance not only to provide accurate predictions, but also to ensure certain levels of robustness. Adversarial Training is a training procedure aiming at providing models that are robust to worst-case perturbations around predefined points. Unfortunately, one of the main issues in adversarial training is that robustness w.r.t. gradient-based attackers is always achieved at the cost of prediction accuracy. In this paper, a new algorithm, called Wasserstein Projected Gradient Descent (WPGD), for adversarial training is proposed. WPGD provides a simple way to obtain cost-sensitive robustness, resulting in a finer control of the robustness-accuracy trade-off. Moreover, WPGD solves an optimal transport problem on the output space of the network and it can efficiently discover directions where robustness is required, allowing to control the directional trade-off between accuracy and robustness. The proposed WPGD is validated in this work on image recognition tasks with different benchmark datasets and architectures. Moreover, real world-like datasets are often unbalanced: this paper shows that when dealing with such type of datasets, the performance of adversarial training are mainly affected in term of standard accuracy.

The use of machine learning (ML) algorithms has significantly increased in neuroscience. However, from the vast extent of possible ML algorithms, which one is the optimal model to predict the target variable? What are the hyperparameters for such a model? Given the plethora of possible answers to these questions, in the last years, automated machine learning (autoML) has been gaining attention. Here, we apply an autoML library called TPOT which uses a tree-based representation of machine learning pipelines and conducts a genetic-programming based approach to find the model and its hyperparameters that more closely predicts the subject's true age. To explore autoML and evaluate its efficacy within neuroimaging datasets, we chose a problem that has been the focus of previous extensive study: brain age prediction. Without any prior knowledge, TPOT was able to scan through the model space and create pipelines that outperformed the state-of-the-art accuracy for Freesurfer-based models using only thickness and volume information for anatomical structure. In particular, we compared the performance of TPOT (mean accuracy error (MAE): $4.612 \pm .124$ years) and a Relevance Vector Regression (MAE $5.474 \pm .140$ years). TPOT also suggested interesting combinations of models that do not match the current most used models for brain prediction but generalise well to unseen data. AutoML showed promising results as a data-driven approach to find optimal models for neuroimaging applications.

--The increasing penetration level of energy generation from renewable sources is demanding for more accurate and reliable forecasting tools to support classic power grid operations (e.g., unit commitment, electricity market clearing or maintenance planning). For this purpose, many physical models have been employed, and more recently many statistical or machine learning algorithms, and data-driven methods in general, are becoming subject of intense research. While generally the power research community focuses on power forecasting at the level of single plants, in a short future horizon of time, in this time we are interested in aggregated macro-area power generation (i.e., in a territory of size greater than 100000 km Real data are used to validate the proposed forecasting methodology on a test set of several months. A. Motivations As the penetration level of Renewable Energy (RE) sources is growing worldwide to meet ever tightening sustainability goals [1], the intermittent and uncertain nature of RE is posing increasing challenges to efficiently manage a power grid, eventually endangering its own stability. In this context, the availability of accurate forecasts of power generation from RE may mitigate the impact of the increasing penetration level and improve the operation of power systems [2].

Tennis is a popular sport worldwide, boasting millions of fans and numerous national and international tournaments. Like many sports, tennis has benefitted from the popularity of rigorous record-keeping of game and player information, as well as the growth of machine learning methods for use in sports analytics. Of particular interest to bettors and betting companies alike is potential use of sports records to predict tennis match outcomes prior to match start. We compiled, cleaned, and used the largest database of tennis match information to date to predict match outcome using fairly simple machine learning methods. Using such methods allows for rapid fit and prediction times to readily incorporate new data and make real-time predictions. We were able to predict match outcomes with upwards of 80% accuracy, much greater than predictions using betting odds alone, and identify serve strength as a key predictor of match outcome. By combining prediction accuracies from three models, we were able to nearly recreate a probability distribution based on average betting odds from betting companies, which indicates that betting companies are using similar information to assign odds to matches. These results demonstrate the capability of relatively simple machine learning models to quite accurately predict tennis match outcomes.

Quantitative structure activity relationships (QSAR) have been around for many years and have been employed in numerous fields from drug design to environmental toxicology. Countless papers have been written employing a wide variety of descriptors and computational methods in order to determine them. Nevertheless, while the jury is still out, it is safe to say that QSAR have not generally lived up to expectations, especially in cases where they are applied to data sets determined after the QSAR models were constructed. But this is true even in many "typical cases" where all of the data are known beforehand and are divided into training and test sets in order to construct and validate a model. Certainly the number of parameters available for use in QSAR models is sufficiently large and diverse to ensure reasonable predictions of bioactivity.

Is the Rectified Adam (RAdam) optimizer actually better than the standard Adam optimizer? According to my 24 experiments, the answer is no, typically not (but there are cases where you do want to use it instead of Adam). In Liu et al.'s 2018 paper, On the Variance of the Adaptive Learning Rate and Beyond, the authors claim that Rectified Adam can obtain: The authors tested their hypothesis on three different datasets, including one NLP dataset and two computer vision datasets (ImageNet and CIFAR-10). In each case Rectified Adam outperformed standard Adam…but failed to outperform standard Stochastic Gradient Descent (SGD)! The Rectified Adam optimizer has some strong theoretical justifications -- but as a deep learning practitioner, you need more than just theory -- you need to see empirical results applied to a variety of datasets. And perhaps more importantly, you need to obtain a mastery level experience operating/driving the optimizer (or a small subset of optimizers) as well. If you haven't yet, go ahead and read part one to ensure you have a good understanding of how the Rectified Adam optimizer works. From there, read today's post to help you understand how to design, code, and run experiments used to compare deep learning optimizers. To learn how to compare Rectified Adam to standard Adam, just keep reading! In the first part of this tutorial, we'll briefly discuss the Rectified Adam optimizer, including how it works and why it's interesting to us as deep learning practitioners.

In this article, we will take a look at the various aspects of the XGBoost library. XGBoost is one of the most reliable machine learning libraries when dealing with huge datasets. In my previous article, I gave a brief introduction about XGBoost on how to use it. This article will mainly aim towards exploring many of the useful features of XGBoost. When using machine learning libraries, it is not only about building state-of-the-art models.