This book is split into 4 parts: Part I: Foundations, Part II: From Theory to Algorithms, Part III: Additional Learning Models, and Part IV: Advanced Theory. If you would like to see the content, click here. If you already have a basic understanding of Python and can apply it, you can further apply these skills and better understand the concepts of probability and statistics. It goes into depth and will take your Machine Learning journey to the next level. Statistics is a major part of Machine Learning, so the more you know the better.

Interactive Imitation Learning (IIL) is a branch of Imitation Learning (IL) where human feedback is provided intermittently during robot execution allowing an online improvement of the robot's behavior. In recent years, IIL has increasingly started to carve out its own space as a promising data-driven alternative for solving complex robotic tasks. The advantages of IIL are its data-efficient, as the human feedback guides the robot directly towards an improved behavior, and its robustness, as the distribution mismatch between the teacher and learner trajectories is minimized by providing feedback directly over the learner's trajectories. Nevertheless, despite the opportunities that IIL presents, its terminology, structure, and applicability are not clear nor unified in the literature, slowing down its development and, therefore, the research of innovative formulations and discoveries. In this article, we attempt to facilitate research in IIL and lower entry barriers for new practitioners by providing a survey of the field that unifies and structures it. In addition, we aim to raise awareness of its potential, what has been accomplished and what are still open research questions. We organize the most relevant works in IIL in terms of human-robot interaction (i.e., types of feedback), interfaces (i.e., means of providing feedback), learning (i.e., models learned from feedback and function approximators), user experience (i.e., human perception about the learning process), applications, and benchmarks. Furthermore, we analyze similarities and differences between IIL and RL, providing a discussion on how the concepts offline, online, off-policy and on-policy learning should be transferred to IIL from the RL literature. We particularly focus on robotic applications in the real world and discuss their implications, limitations, and promising future areas of research.

Network coding allows distributed information sources such as sensors to efficiently compress and transmit data to distributed receivers across a bandwidth-limited network. Classical network coding is largely task-agnostic -- the coding schemes mainly aim to faithfully reconstruct data at the receivers, regardless of what ultimate task the received data is used for. In this paper, we analyze a new task-driven network coding problem, where distributed receivers pass transmitted data through machine learning (ML) tasks, which provides an opportunity to improve efficiency by transmitting salient task-relevant data representations. Specifically, we formulate a task-aware network coding problem over a butterfly network in real-coordinate space, where lossy analog compression through principal component analysis (PCA) can be applied. A lower bound for the total loss function for the formulated problem is given, and necessary and sufficient conditions for achieving this lower bound are also provided. We introduce ML algorithms to solve the problem in the general case, and our evaluation demonstrates the effectiveness of task-aware network coding.

Federated learning (FL), which has gained increasing attention recently, enables distributed devices to train a common machine learning (ML) model for intelligent inference cooperatively without data sharing. However, problems in practical networks, such as non-independent-and-identically-distributed (non-iid) raw data and limited bandwidth, give rise to slow and unstable convergence of the FL training process. To address these issues, we propose a new FL method that can significantly mitigate statistical heterogeneity through the depersonalization mechanism. Particularly, we decouple the global and local optimization objectives by alternating stochastic gradient descent, thus reducing the accumulated variance in local update phases to accelerate the FL convergence. Then we analyze the proposed method detailedly to show the proposed method converging at a sublinear speed in the general non-convex setting. Finally, numerical results are conducted with experiments on public datasets to verify the effectiveness of our proposed method.

Sampling from a high-dimensional distribution is a fundamental task in statistics, engineering, and the sciences. A canonical approach is the Langevin Algorithm, i.e., the Markov chain for the discretized Langevin Diffusion. This is the sampling analog of Gradient Descent. Despite being studied for several decades in multiple communities, tight mixing bounds for this algorithm remain unresolved even in the seemingly simple setting of log-concave distributions over a bounded domain. This paper completely characterizes the mixing time of the Langevin Algorithm to its stationary distribution in this setting (and others). This mixing result can be combined with any bound on the discretization bias in order to sample from the stationary distribution of the continuous Langevin Diffusion. In this way, we disentangle the study of the mixing and bias of the Langevin Algorithm. Our key insight is to introduce a technique from the differential privacy literature to the sampling literature. This technique, called Privacy Amplification by Iteration, uses as a potential a variant of R\'enyi divergence that is made geometrically aware via Optimal Transport smoothing. This gives a short, simple proof of optimal mixing bounds and has several additional appealing properties. First, our approach removes all unnecessary assumptions required by other sampling analyses. Second, our approach unifies many settings: it extends unchanged if the Langevin Algorithm uses projections, stochastic mini-batch gradients, or strongly convex potentials (whereby our mixing time improves exponentially). Third, our approach exploits convexity only through the contractivity of a gradient step -- reminiscent of how convexity is used in textbook proofs of Gradient Descent. In this way, we offer a new approach towards further unifying the analyses of optimization and sampling algorithms.

Numerous research recently proposed integrating Federated Learning (FL) to address the privacy concerns of using machine learning in privacy-sensitive firms. However, the standards of the available frameworks can no longer sustain the rapid advancement and hinder the integration of FL solutions, which can be prominent in advancing the field. In this paper, we propose ModularFed, a research-focused framework that addresses the complexity of FL implementations and the lack of adaptability and extendability in the available frameworks. We provide a comprehensive architecture that assists FL approaches through well-defined protocols to cover three dominant FL paradigms: adaptable workflow, datasets distribution, and third-party application support. Within this architecture, protocols are blueprints that strictly define the framework's components' design, contribute to its flexibility, and strengthen its infrastructure. Further, our protocols aim to enable modularity in FL, supporting third-party plug-and-play architecture and dynamic simulators coupled with major built-in data distributors in the field. Additionally, the framework support wrapping multiple approaches in a single environment to enable consistent replication of FL issues such as clients' deficiency, data distribution, and network latency, which entails a fair comparison of techniques outlying FL technologies. In our evaluation, we examine the applicability of our framework addressing three major FL domains, including statistical distribution and modular-based approaches for resource monitoring and client selection.

This paper focuses on Bayesian inference in a federated learning context (FL). While several distributed MCMC algorithms have been proposed, few consider the specific limitations of FL such as communication bottlenecks and statistical heterogeneity. Recently, Federated Averaging Langevin Dynamics (FALD) was introduced, which extends the Federated Averaging algorithm to Bayesian inference. We obtain a novel tight non-asymptotic upper bound on the Wasserstein distance to the global posterior for FALD. This bound highlights the effects of statistical heterogeneity, which causes a drift in the local updates that negatively impacts convergence. We propose a new algorithm VR-FALD* that uses control variates to correct the client drift. We establish non-asymptotic bounds showing that VR-FALD* is not affected by statistical heterogeneity. Finally, we illustrate our results on several FL benchmarks for Bayesian inference.

Attention mechanisms have recently demonstrated impressive performance on a range of NLP tasks, and attention scores are often used as a proxy for model explainability. However, there is a debate on whether attention weights can, in fact, be used to identify the most important inputs to a model. We approach this question from an information theoretic perspective by measuring the mutual information between the model output and the hidden states. From extensive experiments, we draw the following conclusions: (i) Additive and Deep attention mechanisms are likely to be better at preserving the information between the hidden states and the model output (compared to Scaled Dot-product); (ii) ablation studies indicate that Additive attention can actively learn to explain the importance of its input hidden representations; (iii) when attention values are nearly the same, the rank order of attention values is not consistent with the rank order of the mutual information(iv) Using Gumbel-Softmax with a temperature lower than one, tends to produce a more skewed attention score distribution compared to softmax and hence is a better choice for explainable design; (v) some building blocks are better at preserving the correlation between the ordered list of mutual information and attention weights order (for e.g., the combination of BiLSTM encoder and Additive attention). Our findings indicate that attention mechanisms do have the potential to function as a shortcut to model explanations when they are carefully combined with other model elements.

Given point cloud input, the problem of 6-DoF grasp pose detection is to identify a set of hand poses in SE(3) from which an object can be successfully grasped. This important problem has many practical applications. Here we propose a novel method and neural network model that enables better grasp success rates relative to what is available in the literature. The method takes standard point cloud data as input and works well with single-view point clouds observed from arbitrary viewing directions.

Autism Spectrum Disorder (ASD) is a neuro-developmental syndrome resulting from alterations in the embryological brain before birth. This disorder distinguishes its patients by special socially restricted and repetitive behavior in addition to specific behavioral traits. Hence, this would possibly deteriorate their social behavior among other individuals, as well as their overall interaction within their community. Moreover, medical research has proved that ASD also affects the facial characteristics of its patients, making the syndrome recognizable from distinctive signs within an individual's face. Given that as a motivation behind our work, we propose a novel privacy-preserving federated learning scheme to predict ASD in a certain individual based on their behavioral and facial features, embedding a merging process of both data features through facial feature extraction while respecting patient data privacy. After training behavioral and facial image data on federated machine learning models, promising results are achieved, with 70\% accuracy for the prediction of ASD according to behavioral traits in a federated learning environment, and a 62\% accuracy is reached for the prediction of ASD given an image of the patient's face. Then, we test the behavior of regular as well as federated ML on our merged data, behavioral and facial, where a 65\% accuracy is achieved with the regular logistic regression model and 63\% accuracy with the federated learning model.