We study the complexity of Destructive Shift Bribery. In this problem, we are given an election with a set of candidates and a set of voters (each ranking the candidates from the best to the worst), a despised candidate $d$, a budget $B$, and prices for shifting $d$ back in the voters' rankings. The goal is to ensure that $d$ is not a winner of the election. We show that this problem is polynomial-time solvable for scoring protocols (encoded in unary), the Bucklin and Simplified Bucklin rules, and the Maximin rule, but is NP-hard for the Copeland rule. This stands in contrast to the results for the constructive setting (known from the literature), for which the problem is polynomial-time solvable for $k$-Approval family of rules, but is NP-hard for the Borda, Copeland, and Maximin rules. We complement the analysis of the Copeland rule showing W-hardness for the parameterization by the budget value, and by the number of affected voters. We prove that the problem is W-hard when parameterized by the number of voters even for unit prices. From the positive perspective we provide an efficient algorithm for solving the problem parameterized by the combined parameter the number of candidates and the maximum bribery price (alternatively the number of different bribery prices).

We consider a non-projective class of inhomogeneous random graph models with interpretable parameters and a number of interesting asymptotic properties. Using the results of Bollob\'as et al. [2007], we show that i) the class of models is sparse and ii) depending on the choice of the parameters, the model is either scale-free, with power-law exponent greater than 2, or with an asymptotic degree distribution which is power-law with exponential cut-off. We propose an extension of the model that can accommodate an overlapping community structure. Scalable posterior inference can be performed due to the specific choice of the link probability. We present experiments on five different real-world networks with up to 100,000 nodes and edges, showing that the model can provide a good fit to the degree distribution and recovers well the latent community structure.

Abstract-- Current machine learning techniques proposed to automatically discover a robot kinematics usually rely on a priori information about the robot's structure, sensors properties or end-effector position. This paper proposes a method to estimate a certain aspect of the forward kinematics model with no such information. An internal representation of the end-effector configuration is generated from unstructured proprioceptive and exteroceptive data flow under very limited assumptions. A mapping from the proprioceptive space to this representational space can then be used to control the robot. I. INTRODUCTION One of the problems an autonomous robot must be able to solve is to retrieve basic information about its own topological structure relying on minimal a priori information.

A popular methodology for building binary decision-making classifiers in the presence of imperfect information is to first construct a non-binary "scoring" classifier that is calibrated over all protected groups, and then to post-process this score to obtain a binary decision. We study the feasibility of achieving various fairness properties by post-processing calibrated scores, and then show that deferring post-processors allow for more fairness conditions to hold on the final decision. Specifically, we show: 1. There does not exist a general way to post-process a calibrated classifier to equalize protected groups' positive or negative predictive value (PPV or NPV). For certain "nice" calibrated classifiers, either PPV or NPV can be equalized when the post-processor uses different thresholds across protected groups, though there exist distributions of calibrated scores for which the two measures cannot be both equalized. When the post-processing consists of a single global threshold across all groups, natural fairness properties, such as equalizing PPV in a nontrivial way, do not hold even for "nice" classifiers. 2. When the post-processing is allowed to `defer' on some decisions (that is, to avoid making a decision by handing off some examples to a separate process), then for the non-deferred decisions, the resulting classifier can be made to equalize PPV, NPV, false positive rate (FPR) and false negative rate (FNR) across the protected groups. This suggests a way to partially evade the impossibility results of Chouldechova and Kleinberg et al., which preclude equalizing all of these measures simultaneously. We also present different deferring strategies and show how they affect the fairness properties of the overall system. We evaluate our post-processing techniques using the COMPAS data set from 2016.

This paper presents a new optimisation approach to train Deep Neural Networks (DNNs) with discriminative sequence criteria. At each iteration, the method combines information from the Natural Gradient (NG) direction with local curvature information of the error surface that enables better paths on the parameter manifold to be traversed. The method is derived using an alternative derivation of Taylor's theorem using the concepts of manifolds, tangent vectors and directional derivatives from the perspective of Information Geometry. The efficacy of the method is shown within a Hessian Free (HF) style optimisation framework to sequence train both standard fully-connected DNNs and Time Delay Neural Networks as speech recognition acoustic models. It is shown that for the same number of updates the proposed approach achieves larger reductions in the word error rate (WER) than both NG and HF, and also leads to a lower WER than standard stochastic gradient descent. The paper also addresses the issue of over-fitting due to mismatch between training criterion and Word Error Rate (WER) that primarily arises during sequence training of ReLU-DNN models.

We obtain the first positive results for bounded sample compression in the agnostic regression setting. We show that for p in {1,infinity}, agnostic linear regression with $\ell_p$ loss admits a bounded sample compression scheme. Specifically, we exhibit efficient sample compression schemes for agnostic linear regression in $R^d$ of size $d+1$ under the $\ell_1$ loss and size $d+2$ under the $\ell_\infty$ loss. We further show that for every other $\ell_p$ loss (1 < p < infinity), there does not exist an agnostic compression scheme of bounded size. This refines and generalizes a negative result of David, Moran, and Yehudayoff (2016) for the $\ell_2$ loss. We close by posing a general open question: for agnostic regression with $\ell_1$ loss, does every function class admit a compression scheme of size equal to its pseudo-dimension? This question generalizes Warmuth's classic sample compression conjecture for realizable-case classification (Warmuth, 2003).

ABSTRACT We address the problem of disambiguating large scale catalogs through the definition of an unknown artist clustering task. We explore the use of metric learning techniques to learn artist embeddings directly from audio, and using a dedicated homonym artists dataset, we compare our method with a recent approach that learn similar embeddings using artist classifiers. While both systems have the ability to disambiguate unknown artists relying exclusively on audio, we show that our system is more suitable in the case when enough audio data is available for each artist in the train dataset. We also propose a new negative sampling method for metric learning that takes advantage of side information such as music genre during the learning phase and shows promising results for the artist clustering task. 1. INTRODUCTION 1.1 Motivation With contemporary online music catalogs typically proposing dozens of millions of recordings, a major problem is the lack of an universal and reliable mean to identify music artists. Contrarily to albums' and tracks' ISRC As a direct consequence, the name of an artist remains its defacto identifier in practice although it results in common ambiguity issues. For example, name artist collisions (e.g. Bill Evans is the name of a jazz pianist but also the name of a jazz saxophonist and the name of a blackgrass banjo player) or artist aliases (e.g. Youssou N'Dour vs. Youssou Ndour, Simon & Garfunkel vs Paul Simon and Art Garfunkel, Cat Stevens vs Yusuf Islam) are usual.

Many types of data can be represented as graphs. Edges may correspond to actual links in the data (e.g., users connected by some social network) or to levels of similarity induced from the data (e.g., users having liked a large common set of movies). The resulting graph is typically sparse in the sense that the number of edges is much lower than the total number of node pairs, which makes the data hard to exploit. A standard approach to the analysis of sparse graphs consists in embedding the graph in some vectorial space of low dimension, typically much smaller than the number of nodes [15, 19, 4]. Each node is represented by some vector in the embedding space so that close nodes in the graph (linked either directly or through many short paths in the graph) tend to be represented by close vectors in terms of the Euclidian distance.

In the field of Automated Planning and Scheduling (APS), intelligent agents by virtue require an action model (blueprints of actions whose interleaved executions effectuates transitions of the system state) in order to plan and solve real world problems. It is, however, becoming increasingly cumbersome to codify this model, and is more efficient to learn it from observed plan execution sequences (training data). While the underlying objective is to subsequently plan from this learnt model, most approaches fall short as anything less than a flawless reconstruction of the underlying model renders it unusable in certain domains. This work presents a novel approach using long short-term memory (LSTM) techniques for the acquisition of the underlying action model. We use the sequence labelling capabilities of LSTMs to isolate from an exhaustive model set a model identical to the one responsible for producing the training data.

Combining big data and machine learning algorithms, the power of automatic decision tools induces as much hope as fear. Many recently enacted European legislation (GDPR) and French laws attempt to regulate the use of these tools. Leaving aside the well-identified problems of data confidentiality and impediments to competition, we focus on the risks of discrimination, the problems of transparency and the quality of algorithmic decisions. The detailed perspective of the legal texts, faced with the complexity and opacity of the learning algorithms, reveals the need for important technological disruptions for the detection or reduction of the discrimination risk, and for addressing the right to obtain an explanation of the auto- matic decision. Since trust of the developers and above all of the users (citizens, litigants, customers) is essential, algorithms exploiting personal data must be deployed in a strict ethical framework. In conclusion, to answer this need, we list some ways of controls to be developed: institutional control, ethical charter, external audit attached to the issue of a label.