
The Role of Global Labels in FewShot Classification and How to Infer Them
Fewshot learning (FSL) is a central problem in metalearning, where lea...
read it

Multitask Online Mirror Descent
We introduce and analyze MTOMD, a multitask generalization of Online Mi...
read it

Conditional MetaLearning of Linear Representations
Standard metalearning for representation learning aims to find a common...
read it

Some Hoeffding and Bernsteintype Concentration Inequalities
We prove concentration inequalities for functions of independent random ...
read it

Distributed ZeroOrder Optimization under Adversarial Noise
We study the problem of distributed zeroorder optimization for a class ...
read it

A Perturbation Resilient Framework for Unsupervised Learning
Designing learning algorithms that are resistant to perturbations of the...
read it

Online Model Selection: a Rested Bandit Formulation
Motivated by a natural problem in online model selection with bandit inf...
read it

Convergence Properties of Stochastic Hypergradients
Bilevel optimization problems are receiving increasing attention in mach...
read it

The Advantage of Conditional MetaLearning for Biased Regularization and FineTuning
Biased regularization and finetuning are two recent metalearning appro...
read it

Generalization Properties of Optimal Transport GANs with Latent Distribution Learning
The Generative Adversarial Networks (GAN) framework is a wellestablishe...
read it

Online ParameterFree Learning of Multiple Low Variance Tasks
We propose a method to learn a common bias vector for a growing sequence...
read it

On the Iteration Complexity of Hypergradient Computation
We study a general class of bilevel problems, consisting in the minimiza...
read it

Multisource Domain Adaptation via Weighted Joint Distributions Optimal Transport
The problem of domain adaptation on an unlabeled target dataset using kn...
read it

Exploiting Higher Order Smoothness in Derivativefree Optimization and Continuous Bandits
We study the problem of zeroorder optimization of a strongly convex fun...
read it

Fair Regression with Wasserstein Barycenters
We study the problem of learning a realvalued function that satisfies t...
read it

Metalearning with Stochastic Linear Bandits
We investigate metalearning procedures in the setting of stochastic lin...
read it

Efficient Tensor Kernel methods for sparse regression
Recently, classical kernel methods have been extended by the introductio...
read it

DistanceBased Regularisation of Deep Networks for FineTuning
We investigate approaches to regularisation during finetuning of deep n...
read it

Scheduling the Learning Rate via Hypergradients: New Insights and a New Algorithm
We study the problem of fitting taskspecific learning rate schedules fr...
read it

Learning Fair and Transferable Representations
Developing learning methods which do not discriminate subgroups in the p...
read it

Leveraging Labeled and Unlabeled Data for Consistent Fair Binary Classification
We study the problem of fair binary classification using the notion of E...
read it

Sinkhorn Barycenters with Free Support via FrankWolfe Algorithm
We present a novel algorithm to estimate the barycenter of arbitrary pro...
read it

Learning Discrete Structures for Graph Neural Networks
Graph neural networks (GNNs) are a popular class of machine learning mod...
read it

LearningtoLearn Stochastic Gradient Descent with Biased Regularization
We study the problem of learningtolearn: inferring a learning algorith...
read it

Leveraging LowRank Relations Between Surrogate Tasks in Structured Prediction
We study the interplay between surrogate methods for structured predicti...
read it

Uniform concentration and symmetrization for weak interactions
The method to derive uniform bounds with Gaussian and Rademacher complex...
read it

General Fair Empirical Risk Minimization
We tackle the problem of algorithmic fairness, where the goal is to avoi...
read it

Taking Advantage of Multitask Learning for Fair Classification
A central goal of algorithmic fairness is to reduce bias in automated de...
read it

Fast and Continuous Foothold Adaptation for Dynamic Locomotion through Convolutional Neural Networks
Legged robots can outperform wheeled machines for most navigation tasks ...
read it

FarHO: A Bilevel Programming Package for Hyperparameter Optimization and MetaLearning
In (Franceschi et al., 2018) we proposed a unified mathematical framewor...
read it

Differential Properties of Sinkhorn Approximation for Learning with Wasserstein Distance
Applications of optimal transport have recently gained remarkable attent...
read it

Approximating Hamiltonian dynamics with the Nyström method
Simulating the timeevolution of quantum mechanical systems is BQPhard ...
read it

Incremental LearningtoLearn with Statistical Guarantees
In learningtolearn the goal is to infer a learning algorithm that work...
read it

Empirical bounds for functions with weak interactions
We provide sharp empirical estimates of expectation, variance and normal...
read it

Empirical Risk Minimization under Fairness Constraints
We address the problem of algorithmic fairness: ensuring that sensitive ...
read it

A Bridge Between Hyperparameter Optimization and Larningtolearn
We consider a class of a nested optimization problems involving inner an...
read it

Quantum machine learning: a classical perspective
Recently, increased computational power and data availability, as well a...
read it

Reexamining Low Rank Matrix Factorization for Trace Norm Regularization
Trace norm regularization is a widely used approach for learning low ran...
read it

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

Forward and Reverse GradientBased Hyperparameter Optimization
We study two procedures (reversemode and forwardmode) for computing th...
read it

Regret Bounds for Lifelong Learning
We consider the problem of transfer learning in an online setting. Diffe...
read it

Bounds for VectorValued Function Estimation
We present a framework to derive risk bounds for vectorvalued learning ...
read it

Fitting Spectral Decay with the kSupport Norm
The spectral ksupport norm enjoys good estimation properties in low ran...
read it

New Perspectives on kSupport and Cluster Norms
We study a regularizer which is defined as a parameterized infimum of qu...
read it

The Benefit of Multitask Representation Learning
We discuss a general method to learn data representations from multiple ...
read it

An Inequality with Applications to Structured Sparsity and Multitask Dictionary Learning
From concentration inequalities for the suprema of Gaussian or Rademache...
read it

A New Convex Relaxation for Tensor Completion
We study the problem of learning a tensor from a set of linear measureme...
read it

On Sparsity Inducing Regularization Methods for Machine Learning
During the past years there has been an explosion of interest in learnin...
read it

Excess risk bounds for multitask learning with trace norm regularization
Trace norm regularization is a popular method of multitask learning. We ...
read it

Sparse coding for multitask and transfer learning
We investigate the use of sparse coding and dictionary learning in the c...
read it
Massimiliano Pontil
is this you? claim profile
Professor of Computational Statistics and Machine Learning