Learning to imitate expert behavior given action demonstrations containing high-dimensional, continuous observations and unknown dynamics is a difficult problem in robotic control. Simple approaches based on behavioral cloning (BC) suffer from state distribution shift, while more complex methods that generalize to out-of-distribution states can be difficult to use, since they typically involve adversarial optimization. We propose an alternative that combines the simplicity of BC with the robustness of adversarial imitation learning. The key insight is that under the maximum entropy model of expert behavior, BC corresponds to fitting a soft Q function that maximizes the likelihood of observed actions. This perspective suggests a way to regularize BC so that it generalizes to out-of-distribution states: combine the standard maximum-likelihood objective with a penalty on the soft Bellman error of the soft Q function. We show that this penalty term gives the agent an incentive to take actions that lead it back to demonstrated states when it encounters new states. Experiments show that our method outperforms BC and GAIL on a variety of image-based and low-dimensional environments in Box2D, Atari, and MuJoCo.

Point estimation of class prevalences in the presence of data set shift has been a popular research topic for more than two decades. Less attention has been paid to the construction of confidence and prediction intervals for estimates of class prevalences. One little considered question is whether or not it is necessary for practical purposes to distinguish confidence and prediction intervals. Another question so far not yet conclusively answered is whether or not the discriminatory power of the classifier or score at the basis of an estimation method matters for the accuracy of the estimates of the class prevalences. This paper presents a simulation study aimed at shedding some light on these and other related questions.

Credit risk modelling is an integral part of the global financial system. While there has been great attention paid to neural network models for credit default prediction, such models often lack the required interpretation mechanisms and measures of the uncertainty around their predictions. This work develops and compares Bayesian Neural Networks(BNNs) for credit card default modelling. This includes a BNNs trained by Gaussian approximation and the first implementation of BNNs trained by Hybrid Monte Carlo(HMC) in credit risk modelling. The results on the Taiwan Credit Dataset show that BNNs with Automatic Relevance Determination(ARD) outperform normal BNNs without ARD. The results also show that BNNs trained by Gaussian approximation display similar predictive performance to those trained by the HMC. The results further show that BNN with ARD can be used to draw inferences about the relative importance of different features thus critically aiding decision makers in explaining model output to consumers. The robustness of this result is reinforced by high levels of congruence between the features identified as important using the two different approaches for training BNNs.

We propose to learn deep undirected graphical models (i.e., MRFs), with a non-ELBO objective for which we can calculate exact gradients. In particular, we optimize a saddle-point objective deriving from the Bethe free energy approximation to the partition function. Unlike much recent work in approximate inference, the derived objective requires no sampling, and can be efficiently computed even for very expressive MRFs. We furthermore amortize this optimization with trained inference networks. Experimentally, we find that the proposed approach compares favorably with loopy belief propagation, but is faster, and it allows for attaining better held out log likelihood than other recent approximate inference schemes.

We develop a framework for interacting with uncertain environments in reinforcement learning (RL) by leveraging preferences in the form of utility functions. We claim that there is value in considering different risk measures during learning. In this framework, the preference for risk can be tuned by variation of the parameter $\beta$ and the resulting behavior can be risk-averse, risk-neutral or risk-taking depending on the parameter choice. We evaluate our framework for learning problems with model uncertainty. We measure and control for \emph{epistemic} risk using dynamic programming (DP) and policy gradient-based algorithms. The risk-averse behavior is then compared with the behavior of the optimal risk-neutral policy in environments with epistemic risk.

In classical federated learning a central server coordinates the training of a single model on a massively distributed network of devices. This setting can be naturally extended to a multi-task learning framework, to handle real-world federated datasets that typically show strong non-IID data distributions among devices. Even though federated multi-task learning has been shown to be an effective paradigm for real world datasets, it has been applied only to convex models. In this work we introduce VIRTUAL, an algorithm for federated multi-task learning with non-convex models. In VIRTUAL the federated network of the server and the clients is treated as a star-shaped Bayesian network, and learning is performed on the network using approximated variational inference. We show that this method is effective on real-world federated datasets, outperforming the current state-of-the-art for federated learning.

We introduce Gluon Time Series (GluonTS, available at https://gluon-ts.mxnet.io), a library for deep-learning-based time series modeling. GluonTS simplifies the development of and experimentation with time series models for common tasks such as forecasting or anomaly detection. It provides all necessary components and tools that scientists need for quickly building new models, for efficiently running and analyzing experiments and for evaluating model accuracy.

Variational autoencoders (VAEs) have become one of the most popular deep learning approaches to unsupervised learning and data generation. However, traditional VAEs suffer from the constraint that the latent space must distributionally match a simple prior (e.g. normal, uniform), independent of the initial data distribution. This leads to a number of issues around modeling manifold data, as there is no function with a bounded Jacobian that maps a normal distribution to certain manifolds (e.g. a hypersphere). Similarly, there are not many theoretical guarantees on the encoder and decoder created by the VAE. In this work, we propose a variational autoencoder that maps manifold valued data to its diffusion map coordinates in the latent space, resamples in a neighborhood around a given point in the latent space, and learns a decoder that maps the newly resampled points back to the manifold. The framework is built off of SpectralNet [Shaham et al., 2018a] and is capable of learning this data dependent latent space without computing the eigenfunction of the Laplacian explicitly. We prove that our method is capable of learning a locally bi-Lipschitz map between the manifold and the latent space, and that our resampling method around a point in the latent space $\psi(x)$ maps points back to the manifold around the point $x$, specifically into a neighborbood on the tangent space at the point $x$ on the manifold. We also provide empirical evidence of the benefits of using a diffusion map latent space on manifold data.

Machine Learning, often abbreviated to ML, is a form of learning in which systems use complex computer algorithms to acquire knowledge or skill automatically without being programmed directly. It is considered as a type of AI (Artificial Intelligence) since machines are built with the idea to learn and make decisions from the available data and even improve themselves from experience without requiring human involvement. This is mainly used to maximize the machine's performance. The idea behind ML is based on mathematics, computer science, and statistics. Additionally, great scientists such as Andrey Markov, Thomas Bayes, and Carl Friedrich Gauss have contributed in the invention of statistical models like Markov Chains, Bayes Theorem, and the method of Least-Square respectively which are used a great deal in the Machine Learning algorithms.

In recent years, deep learning has proven to be a viable methodology for surrogate modeling and uncertainty quantification for a vast number of physical systems. However, in their traditional form, such models require a large amount of training data. This is of particular importance for various engineering and scientific applications where data may be extremely expensive to obtain. To overcome this shortcoming, physics-constrained deep learning provides a promising methodology as it only utilizes the governing equations. In this work, we propose a novel auto-regressive dense encoder-decoder convolutional neural network to solve and model transient systems with non-linear dynamics at a computational cost that is potentially magnitudes lower than standard numerical solvers. This model includes a Bayesian framework that allows for uncertainty quantification of the predicted quantities of interest at each time-step. We rigorously test this model on several non-linear transient partial differential equation systems including the turbulence of the Kuramoto-Sivashinsky equation, multi-shock formation and interaction with 1D Burgers' equation and 2D wave dynamics with coupled Burgers' equations. For each system, the predictive results and uncertainty are presented and discussed together with comparisons to the results obtained from traditional numerical analysis methods.