research
∙
09/07/2023
Optimal Transport with Tempered Exponential Measures
In the field of optimal transport, two prominent subfields face each oth...
share
research
∙
08/07/2023
Generative Forests
Tabular data represents one of the most prevalent form of data. When it ...
research
∙
06/08/2023
Boosting with Tempered Exponential Measures
One of the most popular ML algorithms, AdaBoost, can be derived from the...
research
∙
02/17/2023
Smoothly Giving up: Robustness for Simple Models
There is a growing need for models that are interpretable and have reduc...
research
∙
01/27/2023
LegendreTron: Uprising Proper Multiclass Loss Learning
Loss functions serve as the foundation of supervised learning and are of...
research
∙
11/04/2022
Clustering above Exponential Families with Tempered Exponential Measures
The link with exponential families has allowed k-means clustering to be ...
research
∙
05/19/2022
What killed the Convex Booster ?
A landmark negative result of Long and Servedio established a worst-case...
research
∙
01/31/2022
Fair Wrapping for Black-box Predictions
We introduce a new family of techniques to post-process ("wrap") a black...
research
∙
01/26/2022
Generative Trees: Adversarial and Copycat
While Generative Adversarial Networks (GANs) achieve spectacular results...
research
∙
12/23/2021
Manifold Learning Benefits GANs
In this paper, we improve Generative Adversarial Networks by incorporati...
research
∙
06/18/2021
Being Properly Improper
In today's ML, data can be twisted (changed) in various ways, either for...
research
∙
12/01/2020
Data Preprocessing to Mitigate Bias with Boosted Fair Mollifiers
In a recent paper, Celis et al. (2020) introduced a new approach to fair...
research
∙
06/08/2020
All your loss are belong to Bayes
Loss functions are a cornerstone of machine learning and the starting po...
research
∙
03/05/2020
Cumulant-free closed-form formulas for some common (dis)similarities between densities of an exponential family
It is well-known that the Bhattacharyya, Hellinger, Kullback-Leibler, α-...
research
∙
02/11/2020
Generalised Lipschitz Regularisation Equals Distributional Robustness
The problem of adversarial examples has highlighted the need for a theor...
research
∙
02/10/2020
Supervised Learning: No Loss No Cry
Supervised learning requires the specification of a loss function to min...
research
∙
01/26/2020
Boosted and Differentially Private Ensembles of Decision Trees
Boosted ensemble of decision tree (DT) classifiers are extremely popular...
research
∙
12/10/2019
Advances and Open Problems in Federated Learning
Federated learning (FL) is a machine learning setting where many clients...
research
∙
02/19/2019
Proper-Composite Loss Functions in Arbitrary Dimensions
The study of a machine learning problem is in many ways is difficult to ...
research
∙
02/03/2019
Adversarial Networks and Autoencoders: The Primal-Dual Relationship and Generalization Bounds
Since the introduction of Generative Adversarial Networks (GANs) and Var...
research
∙
01/31/2019
New Tricks for Estimating Gradients of Expectations
We derive a family of Monte Carlo estimators for gradients of expectatio...
research
∙
10/22/2018
The Bregman chord divergence
Distances are fundamental primitives whose choice significantly impacts ...
research
∙
09/04/2018
Lipschitz Networks and Distributional Robustness
Robust risk minimisation has several advantages: it has been studied wit...
research
∙
09/01/2018
Hyperparameter Learning for Conditional Mean Embeddings with Rademacher Complexity Bounds
Conditional mean embeddings are nonparametric models that encode conditi...
research
∙
08/13/2018
D-PAGE: Diverse Paraphrase Generation
In this paper, we investigate the diversity aspect of paraphrase generat...
research
∙
06/19/2018
Private Text Classification
Confidential text corpora exist in many forms, but do not allow arbitrar...
research
∙
06/13/2018
Integral Privacy for Density Estimation with Approximation Guarantees
Density estimation is an old and central problem in statistics and machi...
research
∙
06/08/2018
Monge beats Bayes: Hardness Results for Adversarial Training
The last few years have seen extensive empirical study of the robustness...
research
∙
03/22/2018
Boosted Density Estimation Remastered
There has recently been a steadily increase in the iterative approaches ...
research
∙
03/11/2018
Entity Resolution and Federated Learning get a Federated Resolution
Consider two data providers, each maintaining records of different featu...
research
∙
07/14/2017
f-GANs in an Information Geometric Nutshell
Nowozin et al showed last year how to extend the GAN principle to all f-...
research
∙
02/27/2017
Semi-parametric Network Structure Discovery Models
We propose a network structure discovery model for continuous observatio...
research
∙
12/09/2016
A series of maximum entropy upper bounds of the differential entropy
We present a series of closed-form maximum entropy upper bounds for the ...
research
∙
09/22/2016
Large Margin Nearest Neighbor Classification using Curved Mahalanobis Distances
We consider the supervised classification problem of machine learning in...
research
∙
09/13/2016
Making Deep Neural Networks Robust to Label Noise: a Loss Correction Approach
We present a theoretically grounded approach to train deep neural networ...
research
∙
07/01/2016
A scaled Bregman theorem with applications
Bregman divergences play a central role in the design and analysis of a ...
research
∙
06/13/2016
The Crossover Process: Learnability and Data Protection from Inference Attacks
It is usual to consider data protection and learnability as conflicting ...
research
∙
04/06/2016
Fast (1+ε)-approximation of the Löwner extremal matrices of high-dimensional symmetric matrices
Matrix data sets are common nowadays like in biomedical imaging where th...
research
∙
02/08/2016
Loss factorization, weakly supervised learning and label noise robustness
We prove that the empirical risk of most well-known loss functions facto...
research
∙
06/23/2014
Further heuristics for k-means: The merge-and-split heuristic and the (k,l)-means
Finding the optimal k-means clustering is NP-hard in general and many he...
research
∙
01/16/2013
Combining Feature and Prototype Pruning by Uncertainty Minimization
We focus in this paper on dataset reduction techniques for use in k-near...
research
∙
01/08/2010