← Search

Lorenzo Rosasco

55 accepted papers

2025

Computational Efficiency under Covariate Shift in Kernel Ridge Regression

NeurIPS 2025spotlight

This paper addresses the covariate shift problem in the context of nonparametric regression within reproducing kernel Hilbert spaces (RKHSs). Covariate shift arises in supervised learning when the input distributions of the training and test data differ, presenting additional challenges for learning…

Cited by 0SourceScholar
2025

The $\varphi$ Curve: The Shape of Generalization through the Lens of Norm-based Capacity Control

NeurIPS 2025poster

Understanding how the test risk scales with model complexity is a central question in machine learning. Classical theory is challenged by the learning curves observed for large over-parametrized deep networks. Capacity measures based on parameter count typically fail to account for these empirical o…

Cited by 0SourceScholar
2024

RESPRECT: Speeding-up Multi-Fingered Grasping With Residual Reinforcement Learning

RA-L 2024

Deep Reinforcement Learning (DRL) has proven effective in learning control policies using robotic grippers, but much less practical for solving the problem of grasping with dexterous hands – especially on real robotic platforms – due to the high dimensionality of the problem. In this work, we focus

Cited by 11SourcecodeScholar
2024

Sim2Real Bilevel Adaptation for Object Surface Classification using Vision-Based Tactile Sensors

ICRA 2024poster

In this paper, we address the Sim2Real gap in the field of vision-based tactile sensors for classifying object surfaces. We train a Diffusion Model to bridge this gap using a relatively small dataset of real-world images randomly collected from unlabeled everyday objects via the DIGIT sensor. Subseq…

Cited by 2SourcecodeScholar
2023

A Grasp Pose is All You Need: Learning Multi-Fingered Grasping with Deep Reinforcement Learning from Vision and Touch

IROS 2023poster

Multi-fingered robotic hands have potential to enable robots to perform sophisticated manipulation tasks. However, teaching a robot to grasp objects with an anthropomorphic hand is an arduous problem due to the high dimensionality of state and action spaces. Deep Reinforcement Learning (DRL) offers…

Cited by 5SourcecodeScholar
2023

An Optimal Structured Zeroth-order Algorithm for Non-smooth Optimization

NeurIPS 2023poster

Finite-difference methods are a class of algorithms designed to solve black-box optimization problems by approximating a gradient of the target function on a set of directions. In black-box optimization, the non-smooth setting is particularly relevant since, in practice, differentiability and smooth…

Cited by 18SourcePDFScholar
2023

Assumption violations in causal discovery and the robustness of score matching

NeurIPS 2023poster

When domain knowledge is limited and experimentation is restricted by ethical, financial, or time constraints, practitioners turn to observational causal discovery methods to recover the causal structure, exploiting the statistical properties of their data. Because causal discovery without further a…

2023

Estimating Koopman operators with sketching to provably learn large scale dynamical systems

NeurIPS 2023poster

The theory of Koopman operators allows to deploy non-parametric machine learning algorithms to predict and analyze complex dynamical systems. Estimators such as principal component regression (PCR) or reduced rank regression (RRR) in kernel spaces can be shown to provably learn Koopman operators fro…

2023

Heteroscedastic Gaussian Processes and Random Features: Scalable Motion Primitives with Guarantees

CoRL 2023poster

Heteroscedastic Gaussian processes (HGPs) are kernel-based, non-parametric models that can be used to infer nonlinear functions with time-varying noise. In robotics, they can be employed for learning from demonstration as motion primitives, i.e. as a model of the trajectories to be executed by the r…

Cited by 0SourceScholar
2022

ADHERENT: Learning Human-like Trajectory Generators for Whole-body Control of Humanoid Robots

RA-L 2022

<italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">Human-like</i> trajectory generation and footstep planning represent challenging problems in humanoid robotics. Recently, research in computer graphics investigated machine-learning methods for characte

Cited by 22SourceScholar
2022

Ada-BKB: Scalable Gaussian Process Optimization on Continuous Domains by Adaptive Discretization

AISTATS 2022poster

Gaussian process optimization is a successful class of algorithms(e.g. GP-UCB) to optimize a black-box function through sequential evaluations. However, for functions with continuous domains, Gaussian process optimization has to rely on either a fixed discretization of the space, or the solution of…

Cited by 6SourcePDFScholar
2022

Efficient Hyperparameter Tuning for Large Scale Kernel Ridge Regression

AISTATS 2022poster

Kernel methods provide a principled approach to nonparametric learning. While their basic implementations scale poorly to large problems, recent advances showed that approximate solvers can efficiently handle massive datasets. A shortcoming of these solutions is that hyperparameter tuning is not tak…

2022

Learning Dynamical Systems via Koopman Operator Regression in Reproducing Kernel Hilbert Spaces

NeurIPS 2022accept

We study a class of dynamical systems modelled as stationary Markov chains that admit an invariant distribution via the corresponding transfer or Koopman operator. While data-driven algorithms to reconstruct such operators are well known, their relationship with statistical learning is largely unexp…

2022

Mean Nyström Embeddings for Adaptive Compressive Learning

AISTATS 2022poster

Compressive learning is an approach to efficient large scale learning based on sketching an entire dataset to a single mean embedding (the sketch), i.e. a vector of generalized moments. The learning task is then approximately solved as an inverse problem using an adapted parametric model. Previous w…

2022

Multiclass learning with margin: exponential rates with no bias-variance trade-off

ICML 2022spotlight

We study the behavior of error bounds for multiclass classification under suitable margin conditions. For a wide variety of methods we prove that the classification error under a hard-margin condition decreases exponentially fast without any bias-variance trade-off. Different convergence rates can b…

Cited by 5SourcePDFScholar
2022

Nyström Kernel Mean Embeddings

ICML 2022spotlight

Kernel mean embeddings are a powerful tool to represent probability distributions over arbitrary spaces as single points in a Hilbert space. Yet, the cost of computing and storing such embeddings prohibits their direct use in large-scale settings. We propose an efficient approximation procedure base…

2021

Asymptotics of Ridge(less) Regression under General Source Condition

AISTATS 2021poster

We analyze the prediction error of ridge regression in an asymptotic regime where the sample size and dimension go to infinity at a proportional rate. In particular, we consider the role played by the structure of the true regression parameter. We observe that the case of a general deterministic par…

Cited by 107SourcePDFScholar
2021

Fast Object Segmentation Learning with Kernel-based Methods for Robotics

ICRA 2021poster

Object segmentation is a key component in the visual system of a robot that performs tasks like grasping and object manipulation, especially in presence of occlusions. Like many other computer vision tasks, the adoption of deep architectures has made available algorithms that perform this task with…

Cited by 11SourcecodeScholar
2021

Iterative regularization for convex regularizers

AISTATS 2021poster

We study iterative regularization for linear models, when the bias is convex but not necessarily strongly convex. We characterize the stability properties of a primal-dual gradient based approach, analyzing its convergence in the presence of worst case deterministic noise. As a main example, we spec…

Cited by 21SourcePDFScholar
2021

On the Emergence of Whole-Body Strategies From Humanoid Robot Push-Recovery Learning

RA-L 2021

Balancing and push-recovery are essential capabilities enabling humanoid robots to solve complex locomotion tasks. In this context, classical control systems tend to be based on simplified physical models and hard-coded strategies. Although successful in specific scenarios, this approach requires de

Cited by 22SourceScholar
2021

ParK: Sound and Efficient Kernel Ridge Regression by Feature Space Partitions

NeurIPS 2021poster

We introduce ParK, a new large-scale solver for kernel ridge regression. Our approach combines partitioning with random projections and iterative optimization to reduce space and time complexity while provably maintaining the same statistical accuracy. In particular, constructing suitable partitions…

Cited by 10SourcePDFScholar
2021

Structured Prediction for CRiSP Inverse Kinematics Learning With Misspecified Robot Models

RA-L 2021

With the recent advances in machine learning, problems that traditionally would require accurate modeling to be solved analytically can now be successfully approached with data-driven strategies. Among these, computing the inverse kinematics of a redundant robot arm poses a significant challenge due

Cited by 4SourcecodeScholar
2020

Decentralised Learning with Random Features and Distributed Gradient Descent

ICML 2020poster

We investigate the generalisation performance of Distributed Gradient Descent with implicit regularisation and random features in the homogenous setting where a network of agents are given data sampled independently from the same unknown distribution. Along with reducing the memory footprint, random…

Cited by 27SourcePDFScholar
2020

Gain with no Pain: Efficiency of Kernel-PCA by Nyström Sampling

AISTATS 2020poster

In this paper, we analyze a Nyström based approach to efficient large scale kernel principal component analysis (PCA). The latter is a natural nonlinear extension of classical PCA based on considering a nonlinear feature map or the corresponding kernel. Like other kernel approaches, kernel PCA enj…

Cited by 25SourcePDFScholar
2020

Kernel Methods Through the Roof: Handling Billions of Points Efficiently

NeurIPS 2020oral

Kernel methods provide an elegant and principled approach to nonparametric learning, but so far could hardly be used in large scale problems, since naïve implementations scale poorly with data size. Recent advances have shown the benefits of a number of algorithmic ideas, for example combining optim…

2020

Near-linear time Gaussian process optimization with adaptive batching and resparsification

ICML 2020poster

Gaussian processes (GP) are one of the most successful frameworks to model uncertainty. However, GP optimization (e.g., GP-UCB) suffers from major scalability issues. Experimental time grows linearly with the number of evaluations, unless candidates are selected in batches (e.g., using GP-BUCB) and…

2019

Learning to Sequence Multiple Tasks with Competing Constraints

IROS 2019poster

Imitation learning offers a general framework where robots can efficiently acquire novel motor skills from demonstrations of a human teacher. While many promising achievements have been shown, the majority of them are only focused on single-stroke movements, without taking into account the problem o…

Cited by 8SourceScholar
2018

Dirichlet-based Gaussian Processes for Large-scale Calibrated Classification

NeurIPS 2018poster

This paper studies the problem of deriving fast and accurate classification algorithms with uncertainty quantification. Gaussian process classification provides a principled approach, but the corresponding computational burden is hardly sustainable in large-scale problems and devising efficient alte…

2018

On Fast Leverage Score Sampling and Optimal Learning

NeurIPS 2018poster

Leverage score sampling provides an appealing way to perform approximate com- putations for large matrices. Indeed, it allows to derive faithful approximations with a complexity adapted to the problem at hand. Yet, performing leverage scores sampling is a challenge in its own right requiring further…

2018

Speeding-Up Object Detection Training for Robotics with FALKON

IROS 2018poster

Latest deep learning methods for object detection provide remarkable performance, but have limits when used in robotic applications. One of the most relevant issues is the long training time, which is due to the large size and imbalance of the associated training sets, characterized by few positive…

Cited by 27SourceScholar
2017

Consistent Multitask Learning with Nonlinear Output Relations

NeurIPS 2017poster

Key to multitask learning is exploiting the relationships between different tasks to improve prediction performance. Most previous methods have focused on the case where tasks relations can be modeled as linear operators and regularization approaches can be used successfully. However, in practice as…

Cited by 40SourcePDFScholar
2017

Incremental robot learning of new objects with fixed update time

ICRA 2017poster

We consider object recognition in the context of lifelong learning, where a robotic agent learns to discriminate between a growing number of object classes as it accumulates experience about the environment. We propose an incremental variant of the Regularized Least Squares for Classification (RLSC)…

Cited by 51SourcecodeScholar
2016

A Consistent Regularization Approach for Structured Prediction

NeurIPS 2016poster

We propose and analyze a regularization approach for structured prediction problems. We characterize a large class of loss functions that allows to naturally embed structured outputs in a linear space. We exploit this fact to design learning algorithms using a surrogate loss approach and regulari…

Cited by 93SourcePDFScholar
2016

Generalization Properties and Implicit Regularization for Multiple Passes SGM

ICML 2016poster

We study the generalization properties of stochastic gradient methods for learning with convex loss functions and linearly parameterized functions. We show that, in the absence of penalizations or constraints, the stability and approximation properties of the algorithm can be controlled by tuning ei…

Cited by 85SourcePDFScholar
2016

Incremental semiparametric inverse dynamics learning

ICRA 2016

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 informatio

Cited by 51SourceScholar
2016

NYTRO: When Subsampling Meets Early Stopping

AISTATS 2016poster

Early stopping is a well known approach to reduce the time complexity for performing training and model selection of large scale learning machines. On the other hand, memory/space (rather than time) complexity is the main constraint in many applications, and randomized subsampling techniques have b…

2016

Object identification from few examples by improving the invariance of a Deep Convolutional Neural Network

IROS 2016poster

The development of reliable and robust visual recognition systems is a main challenge towards the deployment of autonomous robotic agents in unconstrained environments. Learning to recognize objects requires image representations that are discriminative to relevant information while being invariant…

Cited by 69SourceScholar
2015

Convex Learning of Multiple Tasks and their Structure

ICML 2015poster

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 stru…

Cited by 94SourcePDFScholar