
Decentralised Learning with Random Features and Distributed Gradient Descent
We investigate the generalisation performance of Distributed Gradient De...
read it

Kernel methods through the roof: handling billions of points efficiently
Kernel methods provide an elegant and principled approach to nonparametr...
read it

Regularized ERM on random subspaces
We study a natural extension of classical empirical risk minimization, w...
read it

Interpolation and Learning with Scale Dependent Kernels
We study the learning properties of nonparametric ridgeless least squar...
read it

Implicit regularization for convex regularizers
We study implicit regularization for overparameterized linear models, w...
read it

Asymptotics of Ridge(less) Regression under General Source Condition
We analyze the prediction performance of ridge and ridgeless regression ...
read it

Hyperbolic Manifold Regression
Geometric representation learning has recently shown great promise in se...
read it

Nearlinear Time Gaussian Process Optimization with Adaptive Batching and Resparsification
Gaussian processes (GP) are one of the most successful frameworks to mod...
read it

Constructing fast approximate eigenspaces with application to the fast graph Fourier transforms
We investigate numerically efficient approximations of eigenspaces assoc...
read it

A General Framework for Consistent Structured Prediction with Implicit Loss Embeddings
We propose and analyze a novel theoretical and algorithmic framework for...
read it

Statistical and Computational TradeOffs in Kernel KMeans
We investigate the efficiency of kmeans in terms of both statistical an...
read it

Fast approximation of orthogonal matrices and application to PCA
We study the problem of approximating orthogonal matrices so that their ...
read it

Gain with no Pain: Efficient KernelPCA by Nyström Sampling
In this paper, we propose and study a Nyström based approach to efficien...
read it

MultiScale Vector Quantization with Reconstruction Trees
We propose and study a multiscale approach to vector quantization. We d...
read it

Implicit Regularization of Accelerated Methods in Hilbert Spaces
We study learning properties of accelerated gradient descent methods for...
read it

Reproducing kernel Hilbert spaces on manifolds: Sobolev and Diffusion spaces
We study reproducing kernel Hilbert spaces (RKHS) on a Riemannian mani...
read it

Gaussian Process Optimization with Adaptive Sketching: Scalable and No Regret
Gaussian processes (GP) are a popular Bayesian approach for the optimiza...
read it

Theory III: Dynamics and Generalization in Deep Networks
We review recent observations on the dynamical systems induced by gradie...
read it

Beating SGD Saturation with TailAveraging and Minibatching
While stochastic gradient descent (SGD) is one of the major workhorses i...
read it

A computational model for grid maps in neural populations
Grid cells in the entorhinal cortex, together with place, speed and bord...
read it

On Fast Leverage Score Sampling and Optimal Learning
Leverage score sampling provides an appealing way to perform approximate...
read it

Learning with SGD and Random Features
Sketching and stochastic gradient methods are arguably the most common t...
read it

Manifold Structured Prediction
Structured prediction provides a general framework to deal with supervis...
read it

Dirichletbased Gaussian Processes for Largescale Calibrated Classification
In this paper, we study the problem of deriving fast and accurate classi...
read it

Speedingup Object Detection Training for Robotics with FALKON
Latest deep learning methods for object detection provided remarkable pe...
read it

Iterate averaging as regularization for stochastic gradient descent
We propose and analyze a variant of the classic PolyakRuppert averaging...
read it

Theory of Deep Learning III: explaining the nonoverfitting puzzle
A main puzzle of deep networks revolves around the absence of overfittin...
read it

Optimal Rates for Learning with Nyström Stochastic Gradient Methods
In the setting of nonparametric regression, we propose and study a combi...
read it

Are we Done with Object Recognition? The iCub robot's Perspective
We report on an extensive study of the current benefits and limitations ...
read it

Solving ℓ^pnorm regularization with tensor kernels
In this paper, we discuss how a suitable family of tensor kernels can be...
read it

Generalization Properties of Doubly Online Learning Algorithms
Doubly online learning algorithms are scalable kernel methods that perfo...
read it

FALKON: An Optimal Large Scale Kernel Method
Kernel methods provide a principled way to perform non linear, nonparame...
read it

Consistent Multitask Learning with Nonlinear Output Relations
Key to multitask learning is exploiting relationships between different ...
read it

Convergence of the ForwardBackward Algorithm: Beyond the Worst Case with the Help of Geometry
We provide a comprehensive study of the convergence of forwardbackward ...
read it

Optimal Rates for Multipass Stochastic Gradient Methods
We analyze the learning properties of the stochastic gradient method whe...
read it

Generalization Properties and Implicit Regularization for Multiple Passes SGM
We study the generalization properties of stochastic gradient methods fo...
read it

A Consistent Regularization Approach for Structured Prediction
We propose and analyze a regularization approach for structured predicti...
read it

Incremental Robot Learning of New Objects with Fixed Update Time
We consider object recognition in the context of lifelong learning, wher...
read it

Generalization Properties of Learning with Random Features
We study the generalization properties of ridge regression with random f...
read it

Incremental Semiparametric Inverse Dynamics Learning
This paper presents a novel approach for incremental semiparametric inve...
read it

NYTRO: When Subsampling Meets Early Stopping
Early stopping is a well known approach to reduce the time complexity fo...
read it

Holographic Embeddings of Knowledge Graphs
Learning embeddings of entities and relations is an efficient and versat...
read it

Deep Convolutional Networks are Hierarchical Kernel Machines
In itheory a typical layer of a hierarchical architecture consists of H...
read it

Realworld Object Recognition with Offtheshelf Deep Conv Nets: How Many Objects can iCub Learn?
The ability to visually recognize objects is a fundamental skill for rob...
read it

Learning Multiple Visual Tasks while Discovering their Structure
Multitask learning is a natural approach for computer vision applicatio...
read it

Iterative Regularization for Learning with Convex Loss Functions
We consider the problem of supervised learning with convex loss function...
read it

Learning with incremental iterative regularization
Within a statistical learning setting, we propose and study an iterative...
read it

A Deep Representation for Invariance And Music Classification
Representations in the auditory cortex might be based on mechanisms simi...
read it

Unsupervised Learning of Invariant Representations in Hierarchical Architectures
The present phase of Machine Learning is characterized by supervised lea...
read it

iCub World: Friendly Robots Help Building Good Vision DataSets
In this paper we present and start analyzing the iCub World dataset, an...
read it
Lorenzo Rosasco
is this you? claim profile
Assistant Professor at Università degli Studi di Genova, Visiting Faculty at MIT, team leader at IIT  Istituto Italiano di Tecnologia