Multiple hypothesis testing (MHT) frequently arises in scientific inquiries, and concurrent testing of multiple hypotheses inflates the risk of Type-I errors or false positives, rendering MHT corrections essential. This paper addresses MHT in the context of conformal prediction, a flexible framework for predictive uncertainty quantification. Some conformal applications give rise to simultaneous testing, and positive dependencies among tests typically exist. We introduce max-rank, a novel correction that exploits these dependencies whilst efficiently controlling the family-wise error rate. Inspired by existing permutation-based corrections, max-rank leverages rank order information to improve performance and integrates readily with any conformal procedure. We establish its theoretical and empirical advantages over the common Bonferroni correction and its compatibility with conformal prediction, highlighting the potential to strengthen predictive uncertainty estimates.

Abstract Imitation Learning from observation describes policy learning in a similar way to human learning. An agent’s policy is trained by observing an expert performing a task. Although many state-only imitation learning approaches are based on adversarial imitation learning, one main drawback is that adversarial training is often unstable and lacks a reliable convergence estimator. If the true environment reward is unknown and cannot be used to select the best-performing model, this can result in bad real-world policy performance. We propose a non-adversarial learning-from-observations approach, together with an interpretable convergence and performance metric. Our training objective minimizes the Kulback-Leibler divergence (KLD) between the policy and expert state transition trajectories which can be optimized in a non-adversarial fashion. Such methods demonstrate improved robustness when learned density models guide the optimization. We further improve the sample efficiency by rewriting the KLD minimization as the Soft Actor Critic objective based on a modified reward using additional density models that estimate the environment’s forward and backward dynamics. Finally, we evaluate the effectiveness of our approach on well-known continuous control environments and show state-of-the-art performance while having a reliable performance estimator compared to several recent learning-from-observation methods.

For prediction of interacting agents' trajectories, we propose an end-to-end trainable architecture that hybridizes neural nets with game-theoretic reasoning, has interpretable intermediate representations, and transfers to downstream decision making. It uses a net that reveals preferences from the agents' past joint trajectory, and a differentiable implicit layer that maps these preferences to local Nash equilibria, forming the modes of the predicted future trajectory. Additionally, it learns an equilibrium refinement concept. For tractability, we introduce a new class of continuous potential games and an equilibrium-separating partition of the action space. We provide theoretical results for explicit gradients and soundness. In experiments, we evaluate our approach on two real-world data sets, where we predict highway drivers' merging trajectories, and on a simple decision-making transfer task.

We introduce a multiple instance learning algorithm based on randomized decision trees. Our model extends an existing algorithm by Bloc keel et al. [2] in several ways: 1) We learn a random forest instead of a single tree. 2) We construct the trees by splits based on non-linear boundaries on multiple features at a time. 3) We learn an optimal way of combining the decisions of multiple trees under the multiple instance constraints (i.e. positive bags have at least one positive instance, negative bags have only negative instances). Experiments on the typical benchmark data sets show that this model's prediction performance is clearly better than earlier tree based methods, and is comparable to the global state-of-the-art.

We present the first variational framework for multi-label segmentation on the ray space of 4D light fields. For traditional segmentation of single images, features need to be extracted from the 2D projection of a three-dimensional scene. The associated loss of geometry information can cause severe problems, for example if different objects have a very similar visual appearance. In this work, we show that using a light field instead of an image not only enables to train classifiers which can overcome many of these problems, but also provides an optimal data structure for label optimization by implicitly providing scene geometry information. It is thus possible to consistently optimize label assignment over all views simultaneously. As a further contribution, we make all light fields available online with complete depth and segmentation ground truth data where available, and thus establish the first benchmark data set for light field analysis to facilitate competitive further development of algorithms.

We propose a scheme that allows to partition an image into a previously unknown number of segments, using only minimal supervision in terms of a few must-link and cannot-link annotations. We make no use of regional data terms, learning instead what constitutes a likely boundary between segments. Since boundaries are only implicitly specified through cannot-link constraints, this is a hard and nonconvex latent variable problem. We address this problem in a greedy fashion using a randomized decision tree on features associated with interpixel edges. We use a it structured purity criterion during tree construction and also show how a backtracking strategy can be used to prevent the greedy search from ending up in poor local optima. The proposed strategy is compared with prior art on natural images.

Watershed cuts are among the fastest segmentation algorithms and therefore well suited for interactive segmentation of very large 3D data sets. To minimize the number of user interactions (“seeds”) required until the result is correct, we want the computer to actively query the human for input at the most critical locations, in analogy to active learning. These locations are found by means of suitable uncertainty measures. We propose various such measures for watershed cuts along with a theoretical analysis of some of their properties. Extensive evaluation on two types of 3D electron microscopic volumes of neural tissue shows that measures which estimate the non-local consequences of new user inputs achieve performance close to an oracle endowed with complete knowledge of the ground truth.