Standard empirical risk minimization (ERM) training can produce deep neural network (DNN) models that are accurate on average but under-perform in under-represented population subgroups, especially when there are imbalanced group distributions in the long-tailed training data. Therefore, approaches that improve the accuracy-group robustness trade-off frontier of a DNN model (i.e. improving worst-group accuracy without sacrificing average accuracy, or vice versa) is of crucial importance. Uncertainty-based active learning (AL) can potentially improve the frontier by preferentially sampling underrepresented subgroups to create a more balanced training dataset. However, the quality of uncertainty estimates from modern DNNs tend to degrade in the presence of spurious correlations and dataset bias, compromising the effectiveness of AL for sampling tail groups. In this work, we propose Introspective Self-play (ISP), a simple approach to improve the uncertainty estimation of a deep neural network under dataset bias, by adding an auxiliary introspection task requiring a model to predict the bias for each data point in addition to the label. We show that ISP provably improves the bias-awareness of the model representation and the resulting uncertainty estimates. On two real-world tabular and language tasks, ISP serves as a simple "plug-in" for AL model training, consistently improving both the tail-group sampling rate and the final accuracy-fairness trade-off frontier of popular AL methods.

This article presents a novel telepresence system for advancing aerial manipulation in dynamic and unstructured environments. The proposed system not only features a haptic device, but also a virtual reality (VR) interface that provides real-time 3D displays of the robot's workspace as well as a haptic guidance to its remotely located operator. To realize this, multiple sensors namely a LiDAR, cameras and IMUs are utilized. For processing of the acquired sensory data, pose estimation pipelines are devised for industrial objects of both known and unknown geometries. We further propose an active learning pipeline in order to increase the sample efficiency of a pipeline component that relies on Deep Neural Networks (DNNs) based object detection. All these algorithms jointly address various challenges encountered during the execution of perception tasks in industrial scenarios. In the experiments, exhaustive ablation studies are provided to validate the proposed pipelines. Methodologically, these results commonly suggest how an awareness of the algorithms' own failures and uncertainty (`introspection') can be used tackle the encountered problems. Moreover, outdoor experiments are conducted to evaluate the effectiveness of the overall system in enhancing aerial manipulation capabilities. In particular, with flight campaigns over days and nights, from spring to winter, and with different users and locations, we demonstrate over 70 robust executions of pick-and-place, force application and peg-in-hole tasks with the DLR cable-Suspended Aerial Manipulator (SAM). As a result, we show the viability of the proposed system in future industrial applications.

Mobile robots are ubiquitous. Such vehicles benefit from well-designed and calibrated control algorithms ensuring their task execution under precise uncertainty bounds. Yet, in tasks involving humans in the loop, such as elderly or mobility impaired, the problem takes a new dimension. In such cases, the system needs not only to compensate for uncertainty and volatility in its operation but at the same time to anticipate and offer responses that go beyond robust. Such robots operate in cluttered, complex environments, akin to human residences, and need to face during their operation sensor and, even, actuator faults, and still operate. This is where our thesis comes into the foreground. We propose a new control design framework based on the principles of antifragility. Such a design is meant to offer a high uncertainty anticipation given previous exposure to failures and faults, and exploit this anticipation capacity to provide performance beyond robust. In the current instantiation of antifragile control applied to mobile robot trajectory tracking, we provide controller design steps, the analysis of performance under parametrizable uncertainty and faults, as well as an extended comparative evaluation against state-of-the-art controllers. We believe in the potential antifragile control has in achieving closed-loop performance in the face of uncertainty and volatility by using its exposures to uncertainty to increase its capacity to anticipate and compensate for such events.

This paper presents a novel mechanism design for multi-item auction settings with uncertain bidders' type distributions. Our proposed approach utilizes nonparametric density estimation to accurately estimate bidders' types from historical bids, and is built upon the Vickrey-Clarke-Groves (VCG) mechanism, ensuring satisfaction of Bayesian incentive compatibility (BIC) and $\delta$-individual rationality (IR). To further enhance the efficiency of our mechanism, we introduce two novel strategies for query reduction: a filtering method that screens potential winners' value regions within the confidence intervals generated by our estimated distribution, and a classification strategy that designates the lower bound of an interval as the estimated type when the length is below a threshold value. Simulation experiments conducted on both small-scale and large-scale data demonstrate that our mechanism consistently outperforms existing methods in terms of revenue maximization and query reduction, particularly in large-scale scenarios. This makes our proposed mechanism a highly desirable and effective option for sellers in the realm of multi-item auctions.

This article describes an approach to incorporate expert opinion on observable quantities through the use of a loss function which updates a prior belief as opposed to specifying parameters on the priors. Eliciting information on observable quantities allows experts to provide meaningful information on a quantity familiar to them, in contrast to elicitation on model parameters, which may be subject to interactions with other parameters or non-linear transformations before obtaining an observable quantity. The approach to incorporating expert opinion described in this paper is distinctive in that we do not specify a prior to match an expert's opinion on observed quantity, rather we obtain a posterior by updating the model parameters through a loss function. This loss function contains the observable quantity, expressed a function of the parameters, and is related to the expert's opinion which is typically operationalized as a statistical distribution. Parameters which generate observable quantities which are further from the expert's opinion incur a higher loss, allowing for the model parameters to be estimated based on their fidelity to both the data and expert opinion, with the relative strength determined by the number of observations and precision of the elicited belief. Including expert opinion in this fashion allows for a flexible specification of the opinion and in many situations is straightforward to implement with commonly used probabilistic programming software. We highlight this using three worked examples of varying model complexity including survival models, a multivariate normal distribution and a regression problem.

Automatic crowd counting using density estimation has gained significant attention in computer vision research. As a result, a large number of crowd counting and density estimation models using convolution neural networks (CNN) have been published in the last few years. These models have achieved good accuracy over benchmark datasets. However, attempts to improve the accuracy often lead to higher complexity in these models. In real-time video surveillance applications using drones with limited computing resources, deep models incur intolerable higher inference delay. In this paper, we propose (i) a Lightweight Crowd Density estimation model (LCDnet) for real-time video surveillance, and (ii) an improved training method using curriculum learning (CL). LCDnet is trained using CL and evaluated over two benchmark datasets i.e., DroneRGBT and CARPK. Results are compared with existing crowd models. Our evaluation shows that the LCDnet achieves a reasonably good accuracy while significantly reducing the inference time and memory requirement and thus can be deployed over edge devices with very limited computing resources.

Mixture models of Plackett-Luce (PL) -- one of the most fundamental ranking models -- are an active research area of both theoretical and practical significance. Most previously proposed parameter estimation algorithms instantiate the EM algorithm, often with random initialization. However, such an initialization scheme may not yield a good initial estimate and the algorithms require multiple restarts, incurring a large time complexity. As for the EM procedure, while the E-step can be performed efficiently, maximizing the log-likelihood in the M-step is difficult due to the combinatorial nature of the PL likelihood function (Gormley and Murphy 2008). Therefore, previous authors favor algorithms that maximize surrogate likelihood functions (Zhao et al. 2018, 2020). However, the final estimate may deviate from the true maximum likelihood estimate as a consequence. In this paper, we address these known limitations. We propose an initialization algorithm that can provide a provably accurate initial estimate and an EM algorithm that maximizes the true log-likelihood function efficiently. Experiments on both synthetic and real datasets show that our algorithm is competitive in terms of accuracy and speed to baseline algorithms, especially on datasets with a large number of items.

We propose a continuous optimization framework for discovering a latent directed acyclic graph (DAG) from observational data. Our approach optimizes over the polytope of permutation vectors, the so-called Permutahedron, to learn a topological ordering. Edges can be optimized jointly, or learned conditional on the ordering via a non-differentiable subroutine. Compared to existing continuous optimization approaches our formulation has a number of advantages including: 1. validity: optimizes over exact DAGs as opposed to other relaxations optimizing approximate DAGs; 2. modularity: accommodates any edge-optimization procedure, edge structural parameterization, and optimization loss; 3. end-to-end: either alternately iterates between node-ordering and edge-optimization, or optimizes them jointly. We demonstrate, on real-world data problems in protein-signaling and transcriptional network discovery, that our approach lies on the Pareto frontier of two key metrics, the SID and SHD. In many domains, including cell biology (Sachs et al., 2005), finance (Sanford & Moosa, 2012), and genetics (Zhang et al., 2013), the data generating process is thought to be represented by an underlying directed acylic graph (DAG). Many models rely on DAG assumptions, e.g., causal modeling uses DAGs to model distribution shifts, ensure predictor fairness among subpopulations, or learn agents more sample-efficiently (Kaddour et al., 2022). A key question, with implications ranging from better modeling to causal discovery, is how to recover this unknown DAG from observed data alone. Learning DAGs from observational data alone is fundamentally difficult for two reasons. This riddles the search space with local minima; (ii) Computation: DAG discovery is a costly combinatorial optimization problem over an exponentially large solution space and subject to global acyclicity constraints. To address issue (ii), recent work has proposed continuous relaxations of the DAG learning problem.

While the maximum entropy (MaxEnt) reinforcement learning (RL) framework -- often touted for its exploration and robustness capabilities -- is usually motivated from a probabilistic perspective, the use of deep probabilistic models has not gained much traction in practice due to their inherent complexity. In this work, we propose the adoption of latent variable policies within the MaxEnt framework, which we show can provably approximate any policy distribution, and additionally, naturally emerges under the use of world models with a latent belief state. We discuss why latent variable policies are difficult to train, how naive approaches can fail, then subsequently introduce a series of improvements centered around low-cost marginalization of the latent state, allowing us to make full use of the latent state at minimal additional cost. We instantiate our method under the actor-critic framework, marginalizing both the actor and critic. The resulting algorithm, referred to as Stochastic Marginal Actor-Critic (SMAC), is simple yet effective. We experimentally validate our method on continuous control tasks, showing that effective marginalization can lead to better exploration and more robust training. Our implementation is open sourced at https://github.com/zdhNarsil/Stochastic-Marginal-Actor-Critic.

We study the interplay between the data distribution and Q-learning-based algorithms with function approximation. We provide a unified theoretical and empirical analysis as to how different properties of the data distribution influence the performance of Q-learning-based algorithms. We connect different lines of research, as well as validate and extend previous results. We start by reviewing theoretical bounds on the performance of approximate dynamic programming algorithms. We then introduce a novel four-state MDP specifically tailored to highlight the impact of the data distribution in the performance of Q-learning-based algorithms with function approximation, both online and offline. Finally, we experimentally assess the impact of the data distribution properties on the performance of two offline Q-learning-based algorithms under different environments. According to our results: (i) high entropy data distributions are well-suited for learning in an offline manner; and (ii) a certain degree of data diversity (data coverage) and data quality (closeness to optimal policy) are jointly desirable for offline learning.