Search Results for author:
Found 35 papers, 13 papers with code
Leveraging PAC-Bayes Theory and Gibbs Distributions for Generalization Bounds with Complexity Measures
In statistical learning theory, a generalization bound usually involves a complexity measure imposed by the considered theoretical framework.
Towards Few-Annotation Learning for Object Detection: Are Transformer-based Models More Efficient ?
For specialized and dense downstream tasks such as object detection, labeling data requires expertise and can be very expensive, making few-shot and semi-supervised models much more attractive alternatives.
Proposal-Contrastive Pretraining for Object Detection from Fewer Data
However, for unsupervised pretraining, the popular contrastive learning requires a large batch size and, therefore, a lot of resources.
A Simple Way to Learn Metrics Between Attributed Graphs
Therefore, many metric learning algorithms have been developed in recent years, mainly for Euclidean data in order to improve performance of classification or clustering methods.
Learning Stochastic Majority Votes by Minimizing a PAC-Bayes Generalization Bound
We investigate a stochastic counterpart of majority votes over finite ensembles of classifiers, and study its generalization properties.
Self-Bounding Majority Vote Learning Algorithms by the Direct Minimization of a Tight PAC-Bayesian C-Bound
In the PAC-Bayesian literature, the C-Bound refers to an insightful relation between the risk of a majority vote classifier (under the zero-one loss) and the first two moments of its margin (i. e., the expected margin and the voters' diversity).
A PAC-Bayes Analysis of Adversarial Robustness
We propose the first general PAC-Bayesian generalization bounds for adversarial robustness, that estimate, at test time, how much a model will be invariant to imperceptible perturbations in the input.
A General Framework for the Practical Disintegration of PAC-Bayesian Bounds
PAC-Bayesian bounds are known to be tight and informative when studying the generalization ability of randomized classifiers.
Multiview Variational Graph Autoencoders for Canonical Correlation Analysis
We present a novel multiview canonical correlation analysis model based on a variational approach.
Improving Few-Shot Learning through Multi-task Representation Learning Theory
In this paper, we consider the framework of multi-task representation (MTR) learning where the goal is to use source tasks to learn a representation that reduces the sample complexity of solving a target task.
Putting Theory to Work: From Learning Bounds to Meta-Learning Algorithms
To the best of our knowledge, this is the first contribution that puts the most recent learning bounds of meta-learning theory into practice for the popular task of few-shot classification.
Hierarchical and Unsupervised Graph Representation Learning with Loukas's Coarsening
We propose a novel algorithm for unsupervised graph representation learning with attributed graphs.
A survey on domain adaptation theory: learning bounds and theoretical guarantees
Despite a large amount of different transfer learning scenarios, the main objective of this survey is to provide an overview of the state-of-the-art theoretical results in a specific, and arguably the most popular, sub-field of transfer learning, called domain adaptation.
Metric Learning from Imbalanced Data
A key element of any machine learning algorithm is the use of a function that measures the dis/similarity between data points.
An Adjusted Nearest Neighbor Algorithm Maximizing the F-Measure from Imbalanced Data
In this paper, we address the challenging problem of learning from imbalanced data using a Nearest-Neighbor (NN) algorithm.
Learning Landmark-Based Ensembles with Random Fourier Features and Gradient Boosting
Unlike state-of-the-art Multiple Kernel Learning techniques that make use of a pre-computed dictionary of kernel functions to select from, at each iteration we fit a kernel by approximating it as a weighted sum of Random Fourier Features (RFF) and by optimizing their barycenter.
Deep multi-Wasserstein unsupervised domain adaptation
In unsupervised domain adaptation (DA), 1 aims at learning from labeled source data and fully unlabeled target examples a model with a low error on the target domain.
Near-lossless Binarization of Word Embeddings
Word embeddings are commonly used as a starting point in many NLP models to achieve state-of-the-art performances.
Dict2vec : Learning Word Embeddings using Lexical Dictionaries
Learning word embeddings on large unlabeled corpus has been shown to be successful in improving many natural language tasks.
PAC-Bayes and Domain Adaptation
Firstly, we propose an improvement of the previous approach we proposed in Germain et al. (2013), which relies on a novel distribution pseudodistance based on a disagreement averaging, allowing us to derive a new tighter domain adaptation bound for the target risk.
Joint Distribution Optimal Transportation for Domain Adaptation
This paper deals with the unsupervised domain adaptation problem, where one wants to estimate a prediction function $f$ in a given target domain without any labeled sample by exploiting the knowledge available from a source domain where labels are known.
Mapping Estimation for Discrete Optimal Transport
Most of the computational approaches of Optimal Transport use the Kantorovich relaxation of the problem to learn a probabilistic coupling $\mgamma$ but do not address the problem of learning the underlying transport map $\funcT$ linked to the original Monge problem.
Similarity Learning for Time Series Classification
In this paper, we propose a novel method for learning similarities based on DTW, in order to improve time series classification.
Theoretical Analysis of Domain Adaptation with Optimal Transport
Domain adaptation (DA) is an important and emerging field of machine learning that tackles the problem occurring when the distributions of training (source domain) and test (target domain) data are similar but different.
Regressive Virtual Metric Learning
In this paper, instead of bringing closer examples of the same class and pushing far away examples of different classes we propose to move the examples with respect to virtual points.
A New PAC-Bayesian Perspective on Domain Adaptation
We study the issue of PAC-Bayesian domain adaptation: We want to learn, from a source domain, a majority vote model dedicated to a target one.
PAC-Bayesian Theorems for Domain Adaptation with Specialization to Linear Classifiers
In this paper, we provide two main contributions in PAC-Bayesian theory for domain adaptation where the objective is to learn, from a source distribution, a well-performing majority vote on a different target distribution.
An Improvement to the Domain Adaptation Bound in a PAC-Bayesian context
This paper provides a theoretical analysis of domain adaptation based on the PAC-Bayesian theory.
Algorithmic Robustness for Learning via $(ε, γ, τ)$-Good Similarity Functions
The notion of metric plays a key role in machine learning problems such as classification, clustering or ranking.
Subspace Alignment For Domain Adaptation
We present two approaches to determine the only hyper-parameter in our method corresponding to the size of the subspaces.
Majority Vote of Diverse Classifiers for Late Fusion
Our method is based on an order-preserving pairwise loss adapted to ranking that allows us to improve Mean Averaged Precision measure while taking into account the diversity of the voters that we want to fuse.
Dimension-free Concentration Bounds on Hankel Matrices for Spectral Learning
Existing concentration bounds seem to indicate that the concentration over $H_r$ gets looser with the size of $H_r$, suggesting to make a trade-off between the quantity of used information and the size of $H_r$.
A Survey on Metric Learning for Feature Vectors and Structured Data
The need for appropriate ways to measure the distance or similarity between data is ubiquitous in machine learning, pattern recognition and data mining, but handcrafting such good metrics for specific problems is generally difficult.
Robustness and Generalization for Metric Learning
Metric learning has attracted a lot of interest over the last decade, but the generalization ability of such methods has not been thoroughly studied.
Similarity Learning for Provably Accurate Sparse Linear Classification
In recent years, the crucial importance of metrics in machine learning algorithms has led to an increasing interest for optimizing distance and similarity functions.
