Density destructors are differentiable and invertible transforms that map multivariate PDFs of arbitrary structure (low entropy) into non-structured PDFs (maximum entropy). Multivariate Gaussianization and multivariate equalization are specific examples of this family, which break down the complexity of the original PDF through a set of elementary transforms that progressively remove the structure of the data. We demonstrate how this property of density destructive flows is connected to classical information theory, and how density destructors can be used to get more accurate estimates of information theoretic quantities. Experiments with total correlation and mutual information inmultivariate sets illustrate the ability of density destructors compared to competing methods. These results suggest that information theoretic measures may be an alternative optimization criteria when learning density destructive flows.

By studying the underlying policies of decision-making agents, we can learn about their shortcomings and potentially improve them. Traditionally, this has been done either by examining the agent's implementation, its behaviour while it is being executed, its performance with a reward/fitness function or by visualizing the density of states the agent visits. However, these methods fail to describe the policy's behaviour in complex, high-dimensional environments or do not scale to thousands of policies, which is required when studying training algorithms. We propose policy supervectors for characterizing agents by the distribution of states they visit, adopting successful techniques from the area of speech technology. Policy supervectors can characterize policies regardless of their design philosophy (e.g. rule-based vs. neural networks) and scale to thousands of policies on a single workstation machine. We demonstrate method's applicability by studying the evolution of policies during reinforcement learning, evolutionary training and imitation learning, providing insight on e.g. how the search space of evolutionary algorithms is also reflected in agent's behaviour, not just in the parameters.

Domain adaptation, as a task of reducing the annotation cost in a target domain by exploiting the existing labeled data in an auxiliary source domain, has received a lot of attention in the research community. However, the standard domain adaptation has assumed perfectly observed data in both domains, while in real world applications the existence of missing data can be prevalent. In this paper, we tackle a more challenging domain adaptation scenario where one has an incomplete target domain with partially observed data. We propose an Incomplete Data Imputation based Adversarial Network (IDIAN) model to address this new domain adaptation challenge. In the proposed model, we design a data imputation module to fill the missing feature values based on the partial observations in the target domain, while aligning the two domains via deep adversarial adaption. We conduct experiments on both cross-domain benchmark tasks and a real world adaptation task with imperfect target domains. The experimental results demonstrate the effectiveness of the proposed method.

Human trajectory forecasting is an inherently multi-modal problem. Uncertainty in future trajectories stems from two sources: (a) sources that are known to the agent but unknown to the model, such as long term goals and (b)sources that are unknown to both the agent & the model, such as intent of other agents & irreducible randomness indecisions. We propose to factorize this uncertainty into its epistemic & aleatoric sources. We model the epistemic un-certainty through multimodality in long term goals and the aleatoric uncertainty through multimodality in waypoints& paths. To exemplify this dichotomy, we also propose a novel long term trajectory forecasting setting, with prediction horizons upto a minute, an order of magnitude longer than prior works. Finally, we presentY-net, a scene com-pliant trajectory forecasting network that exploits the pro-posed epistemic & aleatoric structure for diverse trajectory predictions across long prediction horizons.Y-net significantly improves previous state-of-the-art performance on both (a) The well studied short prediction horizon settings on the Stanford Drone & ETH/UCY datasets and (b) The proposed long prediction horizon setting on the re-purposed Stanford Drone & Intersection Drone datasets.

Key components of current cybersecurity methods are the Intrusion Detection Systems (IDSs) were different techniques and architectures are applied to detect intrusions. IDSs can be based either on cross-checking monitored events with a database of known intrusion experiences, known as signature-based, or on learning the normal behavior of the system and reporting whether some anomalous events occur, named anomaly-based. This work is dedicated to the application to the Internet of Things (IoT) network where edge computing is used to support the IDS implementation. New challenges that arise when deploying an IDS in an edge scenario are identified and remedies are proposed. We focus on anomaly-based IDSs, showing the main techniques that can be leveraged to detect anomalies and we present machine learning techniques and their application in the context of an IDS, describing the expected advantages and disadvantages that a specific technique could cause.

Motivated by the EU's "Right To Be Forgotten" regulation, we initiate a study of statistical data deletion problems where users' data are accessible only for a limited period of time. This setting is formulated as an online supervised learning task with \textit{constant memory limit}. We propose a deletion-aware algorithm \texttt{FIFD-OLS} for the low dimensional case, and witness a catastrophic rank swinging phenomenon due to the data deletion operation, which leads to statistical inefficiency. As a remedy, we propose the \texttt{FIFD-Adaptive Ridge} algorithm with a novel online regularization scheme, that effectively offsets the uncertainty from deletion. In theory, we provide the cumulative regret upper bound for both online forgetting algorithms. In the experiment, we showed \texttt{FIFD-Adaptive Ridge} outperforms the ridge regression algorithm with fixed regularization level, and hopefully sheds some light on more complex statistical models.

Forecast combination has been widely applied in the last few decades to improve forecast accuracy. In recent years, the idea of using time series features to construct forecast combination model has flourished in the forecasting area. Although this idea has been proved to be beneficial in several forecast competitions such as the M3 and M4 competitions, it may not be practical in many situations. For example, the task of selecting appropriate features to build forecasting models can be a big challenge for many researchers. Even if there is one acceptable way to define the features, existing features are estimated based on the historical patterns, which are doomed to change in the future, or infeasible in the case of limited historical data. In this work, we suggest a change of focus from the historical data to the produced forecasts to extract features. We calculate the diversity of a pool of models based on the corresponding forecasts as a decisive feature and use meta-learning to construct diversity-based forecast combination models. A rich set of time series are used to evaluate the performance of the proposed method. Experimental results show that our diversity-based forecast combination framework not only simplifies the modelling process but also achieves superior forecasting performance.

Label Smoothing (LS) is an effective regularizer to improve the generalization of state-of-the-art deep models. For each training sample the LS strategy smooths the one-hot encoded training signal by distributing its distribution mass over the non ground-truth classes, aiming to penalize the networks from generating overconfident output distributions. This paper introduces a novel label smoothing technique called Pairwise Label Smoothing (PLS). The PLS takes a pair of samples as input. Smoothing with a pair of ground-truth labels enables the PLS to preserve the relative distance between the two truth labels while further soften that between the truth labels and the other targets, resulting in models producing much less confident predictions than the LS strategy. Also, unlike current LS methods, which typically require to find a global smoothing distribution mass through cross-validation search, PLS automatically learns the distribution mass for each input pair during training. We empirically show that PLS significantly outperforms LS and the baseline models, achieving up to 30% of relative classification error reduction. We also visually show that when achieving such accuracy gains the PLS tends to produce very low winning softmax scores.

The Shapley value solution concept from cooperative game theory has become popular for interpreting ML models, but efficiently estimating Shapley values remains challenging, particularly in the model-agnostic setting. We revisit the idea of estimating Shapley values via linear regression to understand and improve upon this approach. By analyzing KernelSHAP alongside a newly proposed unbiased estimator, we develop techniques to detect its convergence and calculate uncertainty estimates. We also find that that the original version incurs a negligible increase in bias in exchange for a significant reduction in variance, and we propose a variance reduction technique that further accelerates the convergence of both estimators. Finally, we develop a version of KernelSHAP for stochastic cooperative games that yields fast new estimators for two global explanation methods.

Federated learning is a useful framework for centralized learning from distributed data under practical considerations of heterogeneity, asynchrony, and privacy. Federated architectures are frequently deployed in deep learning settings, which generally give rise to non-convex optimization problems. Nevertheless, most existing analysis are either limited to convex loss functions, or only establish first-order stationarity, despite the fact that saddle-points, which are first-order stationary, are known to pose bottlenecks in deep learning. We draw on recent results on the second-order optimality of stochastic gradient algorithms in centralized and decentralized settings, and establish second-order guarantees for a class of federated learning algorithms.