Richard Nock

is this you? claim profile

∙ 0 followers
CSIRO ∙ Australian National University

Adjunct Professor, the Australian National University, the University of Sydney & Senior Principal Researcher, Data61

All your loss are belong to Bayes

Loss functions are a cornerstone of machine learning and the starting po...
06/08/2020 ∙ by Christian Walder, et al. ∙ 0 ∙ share

read it
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-...
03/05/2020 ∙ by Frank Nielsen, et al. ∙ 6 ∙ share

read it
Generalised Lipschitz Regularisation Equals Distributional Robustness

The problem of adversarial examples has highlighted the need for a theor...
02/11/2020 ∙ by Zac Cranko, et al. ∙ 3 ∙ share

read it
Supervised Learning: No Loss No Cry

Supervised learning requires the specification of a loss function to min...
02/10/2020 ∙ by Richard Nock, et al. ∙ 0 ∙ share

read it
Boosted and Differentially Private Ensembles of Decision Trees

Boosted ensemble of decision tree (DT) classifiers are extremely popular...
01/26/2020 ∙ by Richard Nock, et al. ∙ 17 ∙ share

read it
Advances and Open Problems in Federated Learning

Federated learning (FL) is a machine learning setting where many clients...
12/10/2019 ∙ by Peter Kairouz, et al. ∙ 33 ∙ share

read it
Proper-Composite Loss Functions in Arbitrary Dimensions

The study of a machine learning problem is in many ways is difficult to ...
02/19/2019 ∙ by Zac Cranko, et al. ∙ 0 ∙ share

read it
Adversarial Networks and Autoencoders: The Primal-Dual Relationship and Generalization Bounds

Since the introduction of Generative Adversarial Networks (GANs) and Var...
02/03/2019 ∙ by Hisham Husain, et al. ∙ 0 ∙ share

read it
New Tricks for Estimating Gradients of Expectations

We derive a family of Monte Carlo estimators for gradients of expectatio...
01/31/2019 ∙ by Christian J. Walder, et al. ∙ 0 ∙ share

read it
The Bregman chord divergence

Distances are fundamental primitives whose choice significantly impacts ...
10/22/2018 ∙ by Frank Nielsen, et al. ∙ 4 ∙ share

read it
Lipschitz Networks and Distributional Robustness

Robust risk minimisation has several advantages: it has been studied wit...
09/04/2018 ∙ by Zac Cranko, et al. ∙ 0 ∙ share

read it
Hyperparameter Learning for Conditional Mean Embeddings with Rademacher Complexity Bounds

Conditional mean embeddings are nonparametric models that encode conditi...
09/01/2018 ∙ by Kelvin Hsu, et al. ∙ 0 ∙ share

read it
D-PAGE: Diverse Paraphrase Generation

In this paper, we investigate the diversity aspect of paraphrase generat...
08/13/2018 ∙ by Qiongkai Xu, et al. ∙ 0 ∙ share

read it
Private Text Classification

Confidential text corpora exist in many forms, but do not allow arbitrar...
06/19/2018 ∙ by Leif W. Hanlen, et al. ∙ 0 ∙ share

read it
Integral Privacy for Density Estimation with Approximation Guarantees

Density estimation is an old and central problem in statistics and machi...
06/13/2018 ∙ by Hisham Husain, et al. ∙ 0 ∙ share

read it
Monge beats Bayes: Hardness Results for Adversarial Training

The last few years have seen extensive empirical study of the robustness...
06/08/2018 ∙ by Zac Cranko, et al. ∙ 0 ∙ share

read it
Boosted Density Estimation Remastered

There has recently been a steadily increase in the iterative approaches ...
03/22/2018 ∙ by Zac Cranko, et al. ∙ 0 ∙ share

read it
Entity Resolution and Federated Learning get a Federated Resolution

Consider two data providers, each maintaining records of different featu...
03/11/2018 ∙ by Richard Nock, et al. ∙ 0 ∙ share

read it
f-GANs in an Information Geometric Nutshell

Nowozin et al showed last year how to extend the GAN principle to all f-...
07/14/2017 ∙ by Richard Nock, et al. ∙ 0 ∙ share

read it
Semi-parametric Network Structure Discovery Models

We propose a network structure discovery model for continuous observatio...
02/27/2017 ∙ by Amir Dezfouli, et al. ∙ 0 ∙ share

read it
A series of maximum entropy upper bounds of the differential entropy

We present a series of closed-form maximum entropy upper bounds for the ...
12/09/2016 ∙ by Frank Nielsen, et al. ∙ 0 ∙ share

read it
Large Margin Nearest Neighbor Classification using Curved Mahalanobis Distances

We consider the supervised classification problem of machine learning in...
09/22/2016 ∙ by Frank Nielsen, et al. ∙ 0 ∙ share

read it
Making Deep Neural Networks Robust to Label Noise: a Loss Correction Approach

We present a theoretically grounded approach to train deep neural networ...
09/13/2016 ∙ by Giorgio Patrini, et al. ∙ 0 ∙ share

read it
A scaled Bregman theorem with applications

Bregman divergences play a central role in the design and analysis of a ...
07/01/2016 ∙ by Richard Nock, et al. ∙ 0 ∙ share

read it
The Crossover Process: Learnability and Data Protection from Inference Attacks

It is usual to consider data protection and learnability as conflicting ...
06/13/2016 ∙ by Richard Nock, et al. ∙ 0 ∙ share

read it
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...
04/06/2016 ∙ by Frank Nielsen, et al. ∙ 0 ∙ share

read it
Loss factorization, weakly supervised learning and label noise robustness

We prove that the empirical risk of most well-known loss functions facto...
02/08/2016 ∙ by Giorgio Patrini, et al. ∙ 0 ∙ share

read it
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...
06/23/2014 ∙ by Frank Nielsen, et al. ∙ 0 ∙ share

read it
Combining Feature and Prototype Pruning by Uncertainty Minimization

We focus in this paper on dataset reduction techniques for use in k-near...
01/16/2013 ∙ by Marc Sebban, et al. ∙ 0 ∙ share

read it
Boosting k-NN for categorization of natural scenes

The k-nearest neighbors (k-NN) classification rule has proven extremely ...
01/08/2010 ∙ by Paolo Piro, et al. ∙ 0 ∙ share

read it

Richard Nock

Featured Co-authors