Search Results for author:
Found 27 papers, 12 papers with code
Phoneme Discretized Saliency Maps for Explainable Detection of AI-Generated Voice
In this paper, we propose Phoneme Discretized Saliency Maps (PDSM), a discretization algorithm for saliency maps that takes advantage of phoneme boundaries for explainable detection of AI-generated voice.
On the Relationship Between Interpretability and Explainability in Machine Learning
Interpretability and explainability have gained more and more attention in the field of machine learning as they are crucial when it comes to high-stakes decisions and troubleshooting.
Statistical Guarantees for Variational Autoencoders using PAC-Bayesian Theory
Since their inception, Variational Autoencoders (VAEs) have become central in machine learning.
Invariant Causal Set Covering Machines
Rule-based models, such as decision trees, appeal to practitioners due to their interpretable nature.
PAC-Bayesian Generalization Bounds for Adversarial Generative Models
We extend PAC-Bayesian theory to generative models and develop generalization bounds for models based on the Wasserstein distance and the total variation distance.
Seeking Interpretability and Explainability in Binary Activated Neural Networks
We study the use of binary activated neural networks as interpretable and explainable predictors in the context of regression tasks on tabular data; more specifically, we provide guarantees on their expressiveness, present an approach based on the efficient computation of SHAP values for quantifying the relative importance of the features, hidden neurons and even weights.
PAC-Bayesian Learning of Aggregated Binary Activated Neural Networks with Probabilities over Representations
Considering a probability distribution over parameters is known as an efficient strategy to learn a neural network with non-differentiable activation functions.
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 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.
Out-of-distribution detection for regression tasks: parameter versus predictor entropy
Focusing on regression tasks, we choose a simple yet insightful model for this OOD distribution and conduct an empirical evaluation of the ability of various methods to discriminate OOD samples from the data.
Improved PAC-Bayesian Bounds for Linear Regression
In this paper, we improve the PAC-Bayesian error bound for linear regression derived in Germain et al. [10].
PAC-Bayesian Contrastive Unsupervised Representation Learning
Contrastive unsupervised representation learning (CURL) is the state-of-the-art technique to learn representations (as a set of features) from unlabelled data.
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.
Dichotomize and Generalize: PAC-Bayesian Binary Activated Deep Neural Networks
We present a comprehensive study of multilayer neural networks with binary activation, relying on the PAC-Bayesian theory.
Pseudo-Bayesian Learning with Kernel Fourier Transform as Prior
We revisit Rahimi and Recht (2007)'s kernel random Fourier features (RFF) method through the lens of the PAC-Bayesian theory.
Multiview Boosting by Controlling the Diversity and the Accuracy of View-specific Voters
Different experiments on three publicly available datasets show the efficiency of the proposed approach with respect to state-of-art models.
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.
PAC-Bayesian Analysis for a two-step Hierarchical Multiview Learning Approach
We study a two-level multiview learning with more than two views under the PAC-Bayesian framework.
PAC-Bayesian Theory Meets Bayesian Inference
That is, for the negative log-likelihood loss function, we show that the minimization of PAC-Bayesian generalization risk bounds maximizes the Bayesian marginal likelihood.
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.
Domain-Adversarial Training of Neural Networks
Our approach is directly inspired by the theory on domain adaptation suggesting that, for effective domain transfer to be achieved, predictions must be made based on features that cannot discriminate between the training (source) and test (target) domains.
Ranked #2 on
Domain Adaptation
on Synth Digits-to-SVHN
Risk Bounds for the Majority Vote: From a PAC-Bayesian Analysis to a Learning Algorithm
We propose an extensive analysis of the behavior of majority votes in binary classification.
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.
Domain-Adversarial Neural Networks
We propose a training objective that implements this idea in the context of a neural network, whose hidden layer is trained to be predictive of the classification task, but uninformative as to the domain of the input.
From PAC-Bayes Bounds to KL Regularization
We show that standard ell_p-regularized objective functions currently used, such as ridge regression and ell_p-regularized boosting, are obtained from a relaxation of the KL divergence between the quasi uniform posterior and the uniform prior.
