b'Richard Nock'

research

∙ 11/04/2022

Clustering above Exponential Families with Tempered Exponential Measures

The link with exponential families has allowed k-means clustering to be ...

Ehsan Amid, et al. ∙

research

∙ 05/19/2022

What killed the Convex Booster ?

A landmark negative result of Long and Servedio established a worst-case...

Yishay Mansour, et al. ∙

research

∙ 01/31/2022

Fair Wrapping for Black-box Predictions

We introduce a new family of techniques to post-process ("wrap") a black...

Alexander Soen, et al. ∙

research

∙ 01/26/2022

Generative Trees: Adversarial and Copycat

While Generative Adversarial Networks (GANs) achieve spectacular results...

Richard Nock, et al. ∙

research

∙ 12/23/2021

Manifold Learning Benefits GANs

In this paper, we improve Generative Adversarial Networks by incorporati...

Yao Ni, et al. ∙

research

∙ 06/18/2021

Being Properly Improper

In today's ML, data can be twisted (changed) in various ways, either for...

Richard Nock, et al. ∙

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...

Alexander Soen, et al. ∙

research

∙ 06/08/2020

All your loss are belong to Bayes

Loss functions are a cornerstone of machine learning and the starting po...

Christian Walder, et al. ∙

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-...

Frank Nielsen, et al. ∙

research

∙ 02/11/2020

Generalised Lipschitz Regularisation Equals Distributional Robustness

The problem of adversarial examples has highlighted the need for a theor...

Zac Cranko, et al. ∙

research

∙ 02/10/2020

Supervised Learning: No Loss No Cry

Supervised learning requires the specification of a loss function to min...

Richard Nock, et al. ∙

research

∙ 01/26/2020

Boosted and Differentially Private Ensembles of Decision Trees

Boosted ensemble of decision tree (DT) classifiers are extremely popular...

Richard Nock, et al. ∙

research

∙ 12/10/2019

Advances and Open Problems in Federated Learning

Federated learning (FL) is a machine learning setting where many clients...

Peter Kairouz, et al. ∙

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 ...

Zac Cranko, et al. ∙

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...

Hisham Husain, et al. ∙

research

∙ 01/31/2019

New Tricks for Estimating Gradients of Expectations

We derive a family of Monte Carlo estimators for gradients of expectatio...

Christian J. Walder, et al. ∙

research

∙ 10/22/2018

The Bregman chord divergence

Distances are fundamental primitives whose choice significantly impacts ...

Frank Nielsen, et al. ∙

research

∙ 09/04/2018

Lipschitz Networks and Distributional Robustness

Robust risk minimisation has several advantages: it has been studied wit...

Zac Cranko, et al. ∙

research

∙ 09/01/2018

Hyperparameter Learning for Conditional Mean Embeddings with Rademacher Complexity Bounds

Conditional mean embeddings are nonparametric models that encode conditi...

Kelvin Hsu, et al. ∙

research

∙ 08/13/2018

D-PAGE: Diverse Paraphrase Generation

In this paper, we investigate the diversity aspect of paraphrase generat...

Qiongkai Xu, et al. ∙

research

∙ 06/19/2018

Private Text Classification

Confidential text corpora exist in many forms, but do not allow arbitrar...

Leif W. Hanlen, et al. ∙

research

∙ 06/13/2018

Integral Privacy for Density Estimation with Approximation Guarantees

Density estimation is an old and central problem in statistics and machi...

Hisham Husain, et al. ∙

research

∙ 06/08/2018

Monge beats Bayes: Hardness Results for Adversarial Training

The last few years have seen extensive empirical study of the robustness...

Zac Cranko, et al. ∙

research

∙ 03/22/2018

Boosted Density Estimation Remastered

There has recently been a steadily increase in the iterative approaches ...

Zac Cranko, et al. ∙

research

∙ 03/11/2018

Entity Resolution and Federated Learning get a Federated Resolution

Consider two data providers, each maintaining records of different featu...

Richard Nock, et al. ∙

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-...

Richard Nock, et al. ∙

research

∙ 02/27/2017

Semi-parametric Network Structure Discovery Models

We propose a network structure discovery model for continuous observatio...

Amir Dezfouli, et al. ∙

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 ...

Frank Nielsen, et al. ∙

research

∙ 09/22/2016

Large Margin Nearest Neighbor Classification using Curved Mahalanobis Distances

We consider the supervised classification problem of machine learning in...

Frank Nielsen, et al. ∙

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...

Giorgio Patrini, et al. ∙

research

∙ 07/01/2016

A scaled Bregman theorem with applications

Bregman divergences play a central role in the design and analysis of a ...

Richard Nock, et al. ∙

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 ...

Richard Nock, et al. ∙

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...

Frank Nielsen, et al. ∙

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...

Giorgio Patrini, et al. ∙

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...

Frank Nielsen, et al. ∙

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...

Marc Sebban, et al. ∙

research

∙ 01/08/2010

Boosting k-NN for categorization of natural scenes

The k-nearest neighbors (k-NN) classification rule has proven extremely ...

Paolo Piro, et al. ∙

Richard Nock

Featured Co-authors