In this work, we study recommendation systems modelled as contextual multi-armed bandit (MAB) problems. We propose a graph-based recommendation system that learns and exploits the geometry of the user space to create meaningful clusters in the user domain. This reduces the dimensionality of the recommendation problem while preserving the accuracy of MAB. We then study the effect of graph sparsity and clusters size on the MAB performance and provide exhaustive simulation results both in synthetic and in real-case datasets. Simulation results show improvements with respect to state-of-the-art MAB algorithms.

We study the problem of subsampling in differential privacy (DP), a question that is the centerpiece behind many successful differentially private machine learning algorithms. Specifically, we provide a tight upper bound on the R\'enyi Differential Privacy (RDP) (Mironov, 2017) parameters for algorithms that: (1) subsample the dataset, and then (2) apply a randomized mechanism M to the subsample, in terms of the RDP parameters of M and the subsampling probability parameter. This result generalizes the classic subsampling-based "privacy amplification" property of $(\epsilon,\delta)$-differential privacy that applies to only one fixed pair of $(\epsilon,\delta)$, to a stronger version that exploits properties of each specific randomized algorithm and satisfies an entire family of $(\epsilon(\delta),\delta)$-differential privacy for all $\delta\in [0,1]$. Our experiments confirm the advantage of using our techniques over keeping track of $(\epsilon,\delta)$ directly, especially in the setting where we need to compose many rounds of data access.

The paper provides a methodological contribution at the intersection of machine learning and operations research. Namely, we propose a methodology to quickly predict solution summaries (i.e., solution descriptions at a given level of detail) to discrete stochastic optimization problems. We approximate the solutions based on supervised learning and the training dataset consists of a large number of deterministic problems that have been solved independently and offline. Uncertainty regarding a missing subset of the inputs is addressed through sampling and aggregation methods. Our motivating application concerns booking decisions of intermodal containers on double-stack trains. Under perfect information, this is the so-called load planning problem and it can be formulated by means of integer linear programming. However, the formulation cannot be used for the application at hand because of the restricted computational budget and unknown container weights. The results show that standard deep learning algorithms allow one to predict descriptions of solutions with high accuracy in very short time (milliseconds or less).

Class imbalance is an intrinsic characteristic of multi-label data. Most of the labels in multi-label data sets are associated with a small number of training examples, much smaller compared to the size of the data set. Class imbalance poses a key challenge that plagues most multi-label learning methods. Ensemble of Classifier Chains (ECC), one of the most prominent multi-label learning methods, is no exception to this rule, as each of the binary models it builds is trained from all positive and negative examples of a label. To make ECC resilient to class imbalance, we first couple it with random undersampling. We then present two extensions of this basic approach, where we build a varying number of binary models per label and construct chains of different sizes, in order to improve the exploitation of majority examples with approximately the same computational budget. Experimental results on 16 multi-label datasets demonstrate the effectiveness of the proposed approaches in a variety of evaluation metrics.

Typically a classifier trained on a given dataset (source domain) does not performs well if it is tested on data acquired in a different setting (target domain). This is the problem that domain adaptation (DA) tries to overcome and, while it is a well explored topic in computer vision, it is largely ignored in robotic vision where usually visual classification methods are trained and tested in the same domain. Robots should be able to deal with unknown environments, recognize objects and use them in the correct way, so it is important to explore the domain adaptation scenario also in this context. The goal of the project is to define a benchmark and a protocol for multi-modal domain adaptation that is valuable for the robot vision community. With this purpose some of the state-of-the-art DA methods are selected: Deep Adaptation Network (DAN), Domain Adversarial Training of Neural Network (DANN), Automatic Domain Alignment Layers (AutoDIAL) and Adversarial Discriminative Domain Adaptation (ADDA). Evaluations have been done using different data types: RGB only, depth only and RGB-D over the following datasets, designed for the robotic community: RGB-D Object Dataset (ROD), Web Object Dataset (WOD), Autonomous Robot Indoor Dataset (ARID), Big Berkeley Instance Recognition Dataset (BigBIRD) and Active Vision Dataset. Although progresses have been made on the formulation of effective adaptation algorithms and more realistic object datasets are available, the results obtained show that, training a sufficiently good object classifier, especially in the domain adaptation scenario, is still an unsolved problem. Also the best way to combine depth with RGB informations to improve the performance is a point that needs to be investigated more.

Obtaining accurate and well calibrated probability estimates from classifiers is useful in many applications, for example, when minimising the expected cost of classifications. Existing methods of calibrating probability estimates are applied globally, ignoring the potential for improvements by applying a more fine-grained model. We propose probability calibration trees, a modification of logistic model trees that identifies regions of the input space in which different probability calibration models are learned to improve performance. We compare probability calibration trees to two widely used calibration methods---isotonic regression and Platt scaling---and show that our method results in lower root mean squared error on average than both methods, for estimates produced by a variety of base learners.

We introduce a novel paradigm for learning non-parametric drift and diffusion functions for stochastic differential equation (SDE). The proposed model learns to simulate path distributions that match observations with non-uniform time increments and arbitrary sparseness, which is in contrast with gradient matching that does not optimize simulated responses. We formulate sensitivity equations for learning and demonstrate that our general stochastic distribution optimisation leads to robust and efficient learning of SDE systems.

The use of complex models --with many parameters-- is challenging with high-dimensional small-sample problems: indeed, they face rapid overfitting. Such situations are common when data collection is expensive, as in neuroscience, biology, or geology. Dedicated regularization can be crafted to tame overfit, typically via structured penalties. But rich penalties require mathematical expertise and entail large computational costs. Stochastic regularizers such as dropout are easier to implement: they prevent overfitting by random perturbations. Used inside a stochastic optimizer, they come with little additional cost. We propose a structured stochastic regularization that relies on feature grouping. Using a fast clustering algorithm, we define a family of groups of features that capture feature covariations. We then randomly select these groups inside a stochastic gradient descent loop. This procedure acts as a structured regularizer for high-dimensional correlated data without additional computational cost and it has a denoising effect. We demonstrate the performance of our approach for logistic regression both on a sample-limited face image dataset with varying additive noise and on a typical high-dimensional learning problem, brain image classification.

Coreference Resolution is the task of identifying groups of phrases in a text that refer to the same discourse entity. Such referring phrases are called mentions, a set of mentions that all refer to the same 1 discourse entity is called a coreference chain. Annotated corpora are important resources for developing and evaluating automatic coreference resolution methods. Turkish is an agglutinative language and Turkish coreference resolution poses several challenges different from many other languages, in particular the absence of grammatical gender, the possibility of null pronouns in subject and object position, possessive pronouns that can be expressed as suffixes, and ambiguities among possessive and number morphemes, e.g., 'çocukları' can be analysed as'their children' or as'his/her children', depending on context Oflazer and Bozşahin (1994). No coreference resolution corpus exists for Turkish so far. We here describe the result of an effort to create such a corpus based on the METU-Sabanci Turkish Treebank (Say, Zeyrek, Oflazer, and Özge, 2004; Atalay, Oflazer, and Say, 2003; Oflazer, Say, Hakkani-Tür, and Tür, 2003) which is, to the best of our knowledge, the only publicly available Turkish Treebank. Our contributions are as follows.

Interpretable machine learning tackles the important problem that humans cannot understand the behaviors of complex machine learning models and how these classifiers arrive at a particular decision. Although many approaches have been proposed, a comprehensive understanding of the achievements and challenges is still lacking. This paper provides a survey covering existing techniques and methods to increase the interpretability of machine learning models and also discusses the crucial issues to consider in future work such as interpretation design principles and evaluation metrics in order to push forward the area of interpretable machine learning.