arXiv subjects

Lorenzo Rosasco

Publications and source records attributed to Lorenzo Rosasco.

At least 145 records · Page 8Linked to original sources

arXiv2016

A first-order stochastic primal-dual algorithm with correction step

We investigate the convergence properties of a stochastic primal-dual splitting algorithm for solving structured monotone inclusions involving the sum of a cocoercive operator and a composite monotone operator. The proposed method is the stochastic extension to monotone inclusions of a proximal method studied in {\em Y. Drori, S. Sabach, and M. Teboulle, A simple algorithm for a class of nonsmooth convex-concave saddle-point problems, 2015} and {\em I. Loris and C. Verhoeven, On a generalization of the iterative soft-thresholding algorithm for the case of non-separable penalty, 2011} for saddle point problems. It consists in a forward step determined by the stochastic evaluation of the cocoercive operator, a backward step in the dual variables involving the resolvent of the monotone operator, and an additional forward step using the stochastic evaluation of the cocoercive introduced in the first step. We prove weak almost sure convergence of the iterates by showing that the primal-dual sequence generated by the method is stochastic quasi Fejér-monotone with respect to the set of zeros of the considered primal and dual inclusions. Additional results on ergodic convergence in expectation are considered for the special case of saddle point models.

math.OC↗

arXiv2016

Incremental Semiparametric Inverse Dynamics Learning

This paper presents a novel approach for incremental semiparametric inverse dynamics learning. In particular, we consider the mixture of two approaches: Parametric modeling based on rigid body dynamics equations and nonparametric modeling based on incremental kernel methods, with no prior information on the mechanical properties of the system. This yields to an incremental semiparametric approach, leveraging the advantages of both the parametric and nonparametric models. We validate the proposed technique learning the dynamics of one arm of the iCub humanoid robot.

stat.ML↗

arXiv2015

Holographic Embeddings of Knowledge Graphs

Learning embeddings of entities and relations is an efficient and versatile method to perform machine learning on relational data such as knowledge graphs. In this work, we propose holographic embeddings (HolE) to learn compositional vector space representations of entire knowledge graphs. The proposed method is related to holographic models of associative memory in that it employs circular correlation to create compositional representations. By using correlation as the compositional operator HolE can capture rich interactions but simultaneously remains efficient to compute, easy to train, and scalable to very large datasets. In extensive experiments we show that holographic embeddings are able to outperform state-of-the-art methods for link prediction in knowledge graphs and relational learning benchmark datasets.

cs.AI↗

arXiv2015

Modified Fejér sequences and applications

In this note, we propose and study the notion of modified Fejér sequences. Within a Hilbert space setting, we show that it provides a unifying framework to prove convergence rates for objective function values of several optimization algorithms. In particular, our results apply to forward-backward splitting algorithm, incremental subgradient proximal algorithm, and the Douglas-Rachford splitting method including and generalizing known results.

math.OC↗

arXiv2015

Enabling Depth-driven Visual Attention on the iCub Humanoid Robot: Instructions for Use and New Perspectives

The importance of depth perception in the interactions that humans have within their nearby space is a well established fact. Consequently, it is also well known that the possibility of exploiting good stereo information would ease and, in many cases, enable, a large variety of attentional and interactive behaviors on humanoid robotic platforms. However, the difficulty of computing real-time and robust binocular disparity maps from moving stereo cameras often prevents from relying on this kind of cue to visually guide robots' attention and actions in real-world scenarios. The contribution of this paper is two-fold: first, we show that the Efficient Large-scale Stereo Matching algorithm (ELAS) by A. Geiger et al. 2010 for computation of the disparity map is well suited to be used on a humanoid robotic platform as the iCub robot; second, we show how, provided with a fast and reliable stereo system, implementing relatively challenging visual behaviors in natural settings can require much less effort. As a case of study we consider the common situation where the robot is asked to focus the attention on one object close in the scene, showing how a simple but effective disparity-based segmentation solves the problem in this case. Indeed this example paves the way to a variety of other similar applications.

cs.RO↗

arXiv2015

Deep Convolutional Networks are Hierarchical Kernel Machines

In i-theory a typical layer of a hierarchical architecture consists of HW modules pooling the dot products of the inputs to the layer with the transformations of a few templates under a group. Such layers include as special cases the convolutional layers of Deep Convolutional Networks (DCNs) as well as the non-convolutional layers (when the group contains only the identity). Rectifying nonlinearities -- which are used by present-day DCNs -- are one of the several nonlinearities admitted by i-theory for the HW module. We discuss here the equivalence between group averages of linear combinations of rectifying nonlinearities and an associated kernel. This property implies that present-day DCNs can be exactly equivalent to a hierarchy of kernel machines with pooling and non-pooling layers. Finally, we describe a conjecture for theoretically understanding hierarchies of such modules. A main consequence of the conjecture is that hierarchies of trained HW modules minimize memory requirements while computing a selective and invariant representation.

cs.LG↗

arXiv2015

A stochastic inertial forward-backward splitting algorithm for multivariate monotone inclusions

We propose an inertial forward-backward splitting algorithm to compute the zero of a sum of two monotone operators allowing for stochastic errors in the computation of the operators. More precisely, we establish almost sure convergence in real Hilbert spaces of the sequence of iterates to an optimal solution. Then, based on this analysis, we introduce two new classes of stochastic inertial primal-dual splitting methods for solving structured systems of composite monotone inclusions and prove their convergence. Our results extend to the stochastic and inertial setting various types of structured monotone inclusion problems and corresponding algorithmic solutions. Application to minimization problems is discussed.

math.OC↗

arXiv2015

Stochastic inertial primal-dual algorithms

We propose and study a novel stochastic inertial primal-dual approach to solve composite optimization problems. These latter problems arise naturally when learning with penalized regularization schemes. Our analysis provide convergence results in a general setting, that allows to analyze in a unified framework a variety of special cases of interest. Key in our analysis is considering the framework of splitting algorithm for solving a monotone inclusions in suitable product spaces and for a specific choice of preconditioning operators.

math.OC↗

arXiv2015

Learning with incremental iterative regularization

Within a statistical learning setting, we propose and study an iterative regularization algorithm for least squares defined by an incremental gradient method. In particular, we show that, if all other parameters are fixed a priori, the number of passes over the data (epochs) acts as a regularization parameter, and prove strong universal consistency, i.e. almost sure convergence of the risk, as well as sharp finite sample bounds for the iterates. Our results are a step towards understanding the effect of multiple epochs in stochastic gradient techniques in machine learning and rely on integrating statistical and optimization results.

stat.ML↗

arXiv2015

Convex Learning of Multiple Tasks and their Structure

Reducing the amount of human supervision is a key problem in machine learning and a natural approach is that of exploiting the relations (structure) among different tasks. This is the idea at the core of multi-task learning. In this context a fundamental question is how to incorporate the tasks structure in the learning problem.We tackle this question by studying a general computational framework that allows to encode a-priori knowledge of the tasks structure in the form of a convex penalty; in this setting a variety of previously proposed methods can be recovered as special cases, including linear and non-linear approaches. Within this framework, we show that tasks and their structure can be efficiently learned considering a convex optimization problem that can be approached by means of block coordinate methods such as alternating minimization and for which we prove convergence to the global minimum.

cs.LG↗

arXiv2015

Real-world Object Recognition with Off-the-shelf Deep Conv Nets: How Many Objects can iCub Learn?

The ability to visually recognize objects is a fundamental skill for robotics systems. Indeed, a large variety of tasks involving manipulation, navigation or interaction with other agents, deeply depends on the accurate understanding of the visual scene. Yet, at the time being, robots are lacking good visual perceptual systems, which often become the main bottleneck preventing the use of autonomous agents for real-world applications. Lately in computer vision, systems that learn suitable visual representations and based on multi-layer deep convolutional networks are showing remarkable performance in tasks such as large-scale visual recognition and image retrieval. To this regard, it is natural to ask whether such remarkable performance would generalize also to the robotic setting. In this paper we investigate such possibility, while taking further steps in developing a computational vision system to be embedded on a robotic platform, the iCub humanoid robot. In particular, we release a new dataset ({\sc iCubWorld28}) that we use as a benchmark to address the question: {\it how many objects can iCub recognize?} Our study is developed in a learning framework which reflects the typical visual experience of a humanoid robot like the iCub. Experiments shed interesting insights on the strength and weaknesses of current computer vision approaches applied in real robotic settings.

cs.RO↗

arXiv2015

Learning Multiple Visual Tasks while Discovering their Structure

Multi-task learning is a natural approach for computer vision applications that require the simultaneous solution of several distinct but related problems, e.g. object detection, classification, tracking of multiple agents, or denoising, to name a few. The key idea is that exploring task relatedness (structure) can lead to improved performances. In this paper, we propose and study a novel sparse, non-parametric approach exploiting the theory of Reproducing Kernel Hilbert Spaces for vector-valued functions. We develop a suitable regularization framework which can be formulated as a convex optimization problem, and is provably solvable using an alternating minimization approach. Empirical tests show that the proposed method compares favorably to state of the art techniques and further allows to recover interpretable structures, a problem of interest in its own right.

cs.LG↗

arXiv2015

Iterative Regularization for Learning with Convex Loss Functions

We consider the problem of supervised learning with convex loss functions and propose a new form of iterative regularization based on the subgradient method. Unlike other regularization approaches, in iterative regularization no constraint or penalization is considered, and generalization is achieved by (early) stopping an empirical iteration. We consider a nonparametric setting, in the framework of reproducing kernel Hilbert spaces, and prove finite sample bounds on the excess risk under general regularity conditions. Our study provides a new class of efficient regularized learning algorithms and gives insights on the interplay between statistics and optimization in machine learning.

stat.ML↗

arXiv2015

On Invariance and Selectivity in Representation Learning

We discuss data representation which can be learned automatically from data, are invariant to transformations, and at the same time selective, in the sense that two points have the same representation only if they are one the transformation of the other. The mathematical results here sharpen some of the key claims of i-theory -- a recent theory of feedforward processing in sensory cortex.

cs.LG↗

arXiv2015

A Stochastic forward-backward splitting method for solving monotone inclusions in Hilbert spaces

We propose and analyze the convergence of a novel stochastic forward-backward splitting algorithm for solving monotone inclusions given by the sum of a maximal monotone operator and a single-valued maximal monotone cocoercive operator. This latter framework has a number of interesting special cases, including variational inequalities and convex minimization problems, while stochastic approaches are practically relevant to account for perturbations in the data. The algorithm we propose is a stochastic extension of the classical deterministic forward-backward method, and is obtained considering the composition of the resolvent of the maximal monotone operator with a forward step based on a stochastic estimate of the single-valued operator. Our study provides a non-asymptotic error analysis in expectation for the strongly monotone case, as well as almost sure convergence under weaker assumptions. The approach we consider allows to avoid averaging, a feature critical when considering methods based on sparsity, and, for minimization problems, it allows to obtain convergence rates matching those obtained by stochastic extensions of so called accelerated methods. Stochastic quasi Fejer's sequences are a key technical tool to prove almost sure convergence.

math.OC↗

arXiv2014

Learning Sets with Separating Kernels

We consider the problem of learning a set from random samples. We show how relevant geometric and topological properties of a set can be studied analytically using concepts from the theory of reproducing kernel Hilbert spaces. A new kind of reproducing kernel, that we call separating kernel, plays a crucial role in our study and is analyzed in detail. We prove a new analytic characterization of the support of a distribution, that naturally leads to a family of provably consistent regularized learning algorithms and we discuss the stability of these methods with respect to random sampling. Numerical experiments show that the approach is competitive, and often better, than other state of the art techniques.

stat.ML↗

arXiv2014

Convergence of Stochastic Proximal Gradient Algorithm

We prove novel convergence results for a stochastic proximal gradient algorithm suitable for solving a large class of convex optimization problems, where a convex objective function is given by the sum of a smooth and a possibly non-smooth component. We consider the iterates convergence and derive $O(1/n)$ non asymptotic bounds in expectation in the strongly convex case, as well as almost sure convergence results under weaker assumptions. Our approach allows to avoid averaging and weaken boundedness assumptions which are often considered in theoretical studies and might not be satisfied in practice.

math.OC↗

arXiv2014

On the Sample Complexity of Subspace Learning

A large number of algorithms in machine learning, from principal component analysis (PCA), and its non-linear (kernel) extensions, to more recent spectral embedding and support estimation methods, rely on estimating a linear subspace from samples. In this paper we introduce a general formulation of this problem and derive novel learning error estimates. Our results rely on natural assumptions on the spectral properties of the covariance operator associated to the data distribu- tion, and hold for a wide class of metrics between subspaces. As special cases, we discuss sharp error estimates for the reconstruction properties of PCA and spectral support estimation. Key to our analysis is an operator theoretic approach that has broad applicability to spectral learning methods.

stat.ML↗