Programming-by-example technologies are being deployed in industrial products for real-time synthesis of various kinds of data transformations. These technologies rely on the user to provide few representative examples of the transformation task. Motivated by the need to find the most pertinent question to ask the user, in this paper, we introduce the {\em significant questions problem}, and show that it is hard in general. We then develop an information-theoretic greedy approach for solving the problem. We justify the greedy algorithm using the conditional entropy result, which informally says that the question that achieves the maximum information gain is the one that we know least about. In the context of interactive program synthesis, we use the above result to develop an {\em{active program learner}} that generates the significant inputs to pose as queries to the user in each iteration. The procedure requires extending a {\em{passive program learner}} to a {\em{sampling program learner}} that is able to sample candidate programs from the set of all consistent programs to enable estimation of information gain. It also uses clustering of inputs based on features in the inputs and the corresponding outputs to sample a small set of candidate significant inputs. Our active learner is able to tradeoff false negatives for false positives and converge in a small number of iterations on a real-world dataset of %around 800 string transformation tasks.

In the next coming years, space activities are expected to undergo a radical transformation with the emergence of new satellite systems or new services which will incorporate the contributions of artificial intelligence and machine learning defined as covering a wide range of innovations from autonomous objects with their own decision-making power to increasingly sophisticated services exploiting very large volumes of information from space. This chapter identifies some of the legal and ethical challenges linked to its use. These legal and ethical challenges call for solutions which the international treaties in force are not sufficient to determine and implement. For this reason, a legal methodology must be developed that makes it possible to link intelligent systems and services to a system of rules applicable thereto. It discusses existing legal AI-based tools amenable for making space law actionable, interoperable and machine readable for future compliance tools.

We are interested in models where actions are deterministic, This can be done through contrastive explanations [5], durationless, and can be performed one at a time. We also which focus on explaining the difference between a factual assume a known initial state and goal. Traditionally, ethical event A and a contrasting event B. To produce these explanations, principles of single decisions are evaluated [1]. In the context one must reason about the hypothetical alternative B, of AI Planning this means analysing a massive number of which likely means constructing an alternative plan where B isolated decisions that may not make sense without the is included rather than A. The original model is constrained context in which they are being made. Therefore, it is to produce a hypothetical planning model (HModel). The preferable to evaluate the ethical contents of a plan as a solution to the HModel is the hypothetical plan (HPlan) that whole. Lindner et al. [2] describe an approach to judging contains the contrast case expected by the user.

Much of the current work on reinforcement learning studies episodic settings, where the agent is reset between trials to an initial state distribution, often with well-shaped reward functions. Non-episodic settings, where the agent must learn through continuous interaction with the world without resets, and where the agent receives only delayed and sparse reward signals, is substantially more difficult, but arguably more realistic considering real-world environments do not present the learner with a convenient "reset mechanism" and easy reward shaping. In this paper, instead of studying algorithmic improvements that can address such non-episodic and sparse reward settings, we instead study the kinds of environment properties that can make learning under such conditions easier. Understanding how properties of the environment impact the performance of reinforcement learning agents can help us to structure our tasks in ways that make learning tractable. We first discuss what we term "environment shaping" -- modifications to the environment that provide an alternative to reward shaping, and may be easier to implement. We then discuss an even simpler property that we refer to as "dynamism," which describes the degree to which the environment changes independent of the agent's actions and can be measured by environment transition entropy. Surprisingly, we find that even this property can substantially alleviate the challenges associated with non-episodic RL in sparse reward settings. We provide an empirical evaluation on a set of new tasks focused on non-episodic learning with sparse rewards. Through this study, we hope to shift the focus of the community towards analyzing how properties of the environment can affect learning and the ultimate type of behavior that is learned via RL.

Multi-step (also called n-step) methods in reinforcement learning (RL) have been shown to be more efficient than the 1-step method due to faster propagation of the reward signal, both theoretically and empirically, in tasks exploiting tabular representation of the value-function. Recently, research in Deep Reinforcement Learning (DRL) also shows that multi-step methods improve learning speed and final performance in applications where the value-function and policy are represented with deep neural networks. However, there is a lack of understanding about what is actually contributing to the boost of performance. In this work, we analyze the effect of multi-step methods on alleviating the overestimation problem in DRL, where multi-step experiences are sampled from a replay buffer. Specifically building on top of Deep Deterministic Policy Gradient (DDPG), we propose Multi-step DDPG (MDDPG), where different step sizes are manually set, and its variant called Mixed Multi-step DDPG (MMDDPG) where an average over different multi-step backups is used as update target of Q-value function. Empirically, we show that both MDDPG and MMDDPG are significantly less affected by the overestimation problem than DDPG with 1-step backup, which consequently results in better final performance and learning speed. We also discuss the advantages and disadvantages of different ways to do multi-step expansion in order to reduce approximation error, and expose the tradeoff between overestimation and underestimation that underlies offline multi-step methods. Finally, we compare the computational resource needs of Twin Delayed Deep Deterministic Policy Gradient (TD3), a state-of-art algorithm proposed to address overestimation in actor-critic methods, and our proposed methods, since they show comparable final performance and learning speed.

We introduce MotioNet, a deep neural network that directly reconstructs the motion of a 3D human skeleton from monocular video.While previous methods rely on either rigging or inverse kinematics (IK) to associate a consistent skeleton with temporally coherent joint rotations, our method is the first data-driven approach that directly outputs a kinematic skeleton, which is a complete, commonly used, motion representation. At the crux of our approach lies a deep neural network with embedded kinematic priors, which decomposes sequences of 2D joint positions into two separate attributes: a single, symmetric, skeleton, encoded by bone lengths, and a sequence of 3D joint rotations associated with global root positions and foot contact labels. These attributes are fed into an integrated forward kinematics (FK) layer that outputs 3D positions, which are compared to a ground truth. In addition, an adversarial loss is applied to the velocities of the recovered rotations, to ensure that they lie on the manifold of natural joint rotations. The key advantage of our approach is that it learns to infer natural joint rotations directly from the training data, rather than assuming an underlying model, or inferring them from joint positions using a data-agnostic IK solver. We show that enforcing a single consistent skeleton along with temporally coherent joint rotations constrains the solution space, leading to a more robust handling of self-occlusions and depth ambiguities.

In this paper, we initiate the study of fair clustering that ensures distributional similarity among similar individuals. In response to improving fairness in machine learning, recent papers have investigated fairness in clustering algorithms and have focused on the paradigm of statistical parity/group fairness. These efforts attempt to minimize bias against some protected groups in the population. However, to the best of our knowledge, the alternative viewpoint of individual fairness, introduced by Dwork et al. (ITCS 2012) in the context of classification, has not been considered for clustering so far. Similar to Dwork et al., we adopt the individual fairness notion which mandates that similar individuals should be treated similarly for clustering problems. We use the notion of $f$-divergence as a measure of statistical similarity that significantly generalizes the ones used by Dwork et al. We introduce a framework for assigning individuals, embedded in a metric space, to probability distributions over a bounded number of cluster centers. The objective is to ensure (a) low cost of clustering in expectation and (b) individuals that are close to each other in a given fairness space are mapped to statistically similar distributions. We provide an algorithm for clustering with $p$-norm objective ($k$-center, $k$-means are special cases) and individual fairness constraints with provable approximation guarantee. We extend this framework to include both group fairness and individual fairness inside the protected groups. Finally, we observe conditions under which individual fairness implies group fairness. We present extensive experimental evidence that justifies the effectiveness of our approach.

Density-ratio estimation via classification is a cornerstone of unsupervised learning. It has provided the foundation for state-of-the-art methods in representation learning and generative modelling, with the number of use-cases continuing to proliferate. However, it suffers from a critical limitation: it fails to accurately estimate ratios p/q for which the two densities differ significantly. Empirically, we find this occurs whenever the KL divergence between p and q exceeds tens of nats. To resolve this limitation, we introduce a new framework, telescoping density-ratio estimation (TRE), that enables the estimation of ratios between highly dissimilar densities in high-dimensional spaces. Our experiments demonstrate that TRE can yield substantial improvements over existing single-ratio methods for mutual information estimation, representation learning and energy-based modelling.

Typical architectures of Generative AdversarialNetworks make use of a unimodal latent distribution transformed by a continuous generator. Consequently, the modeled distribution always has connected support which is cumbersome when learning a disconnected set of manifolds. We formalize this problem by establishing a no free lunch theorem for the disconnected manifold learning stating an upper bound on the precision of the targeted distribution. This is done by building on the necessary existence of a low-quality region where the generator continuously samples data between two disconnected modes. Finally, we derive a rejection sampling method based on the norm of generators Jacobian and show its efficiency on several generators including BigGAN.

Federated learning provides a framework to address the challenges of distributed computing, data ownership and privacy over a large number of distributed clients with low computational and communication capabilities. In this paper, we study the problem of learning the exact support of sparse linear regression in the federated learning setup. We provide a simple communication efficient algorithm which only needs one-shot communication with the centralized server to compute the exact support. Our method does not require the clients to solve any optimization problem and thus, can be run on devices with low computational capabilities. Our method is naturally robust to the problems of client failure, model poisoning and straggling clients. We formally prove that our method requires a number of samples per client that is polynomial with respect to the support size, but independent of the dimension of the problem. We require the number of distributed clients to be logarithmic in the dimension of the problem. If the predictor variables are mutually independent then the overall sample complexity matches the optimal sample complexity of the non-federated centralized setting. Furthermore, our method is easy to implement and has an overall polynomial time complexity.