Robert C. Williamson
62 publications
8 venues
H Index 25
Affiliation
Universitaet Tuebingen, GermanyLinks
| Name | Venue | Year | citations |
|---|---|---|---|
Random Classification Noise does not defeat All Convex Potential Boosters Irrespective of Model Choice.
|
ICML | 2023 | 0 |
| PAC-Bayesian Bound for the Conditional Value at Risk.
|
NIPS/NeurIPS | 2020 | 12 |
| Fairness risk measures.
|
ICML | 2019 | 81 |
| A Primal-Dual link between GANs and Autoencoders.
|
NIPS/NeurIPS | 2019 | 13 |
| Costs and Benefits of Fair Representation Learning.
|
AIES | 2019 | 40 |
| Lossless or Quantized Boosting with Integer Arithmetic.
|
ICML | 2019 | 6 |
| Constant Regret, Generalized Mixability, and Mirror Descent.
|
NIPS/NeurIPS | 2018 | 5 |
| A Theory of Learning with Corrupted Labels.
|
JMLR | 2017 | 58 |
| f-GANs in an Information Geometric Nutshell.
|
NIPS/NeurIPS | 2017 | 23 |
| Bipartite Ranking: a Risk-Theoretic Perspective.
|
JMLR | 2016 | 25 |
| Composite Multiclass Losses.
|
JMLR | 2016 | 0 |
| Exp-Concavity of Proper Composite Losses.
|
COLT | 2015 | 7 |
| Fast rates in statistical and online learning.
|
JMLR | 2015 | 84 |
| Learning with Symmetric Label Noise: The Importance of Being Unhinged.
|
NIPS/NeurIPS | 2015 | 229 |
| Generalized Mixability via Entropic Duality.
|
COLT | 2015 | 0 |
| Bayes-Optimal Scorers for Bipartite Ranking.
|
COLT | 2014 | 6 |
| On the Consistency of Output Code Based Learning Algorithms for Multiclass Learning Problems.
|
COLT | 2014 | 13 |
| The Geometry of Losses.
|
COLT | 2014 | 14 |
| From Stochastic Mixability to Fast Rates.
|
NIPS/NeurIPS | 2014 | 16 |
| Elicitation and Identification of Properties.
|
COLT | 2014 | 76 |
| Mixability in Statistical Learning.
|
NIPS/NeurIPS | 2012 | 16 |
| Divergences and Risks for Multiclass Experiments.
|
COLT | 2012 | 23 |
| The Convexity and Design of Composite Multiclass Losses.
|
ICML | 2012 | 4 |
| Mixability is Bayes Risk Curvature Relative to Log Loss.
|
JMLR | 2012 | 0 |
| Mixability is Bayes Risk Curvature Relative to Log Loss.
|
COLT | 2011 | 20 |
| Composite Multiclass Losses.
|
NIPS/NeurIPS | 2011 | 73 |
| Information, Divergence and Risk for Binary Experiments.
|
JMLR | 2011 | 0 |
| Convexity of Proper Composite Binary Losses.
|
AISTATS | 2010 | 0 |
| Composite Binary Losses.
|
JMLR | 2010 | 0 |
| Surrogate regret bounds for proper losses.
|
ICML | 2009 | 50 |
| Generalised Pinsker Inequalities.
|
COLT | 2009 | 33 |
| The Need for Open Source Software in Machine Learning.
|
JMLR | 2007 | 214 |
| Learning the Kernel with Hyperkernels.
|
JMLR | 2005 | 367 |
| Online Bayes Point Machines.
|
PAKDD | 2003 | 20 |
| Hyperkernels.
|
NIPS/NeurIPS | 2002 | 64 |
| Agnostic Learning Nonconvex Function Classes.
|
COLT | 2002 | 8 |
| Algorithmic Luckiness.
|
JMLR | 2002 | 0 |
| Online Learning with Kernels.
|
NIPS/NeurIPS | 2001 | 1086 |
| Algorithmic Luckiness.
|
NIPS/NeurIPS | 2001 | 61 |
| Kernel Machines and Boolean Functions.
|
NIPS/NeurIPS | 2001 | 18 |
| Prior Knowledge and Preferential Structures in Gradient Descent Learning Algorithms.
|
JMLR | 2001 | 26 |
| Regularized Principal Manifolds.
|
JMLR | 2001 | 0 |
| Regularization with Dot-Product Kernels.
|
NIPS/NeurIPS | 2000 | 114 |
| From Margin to Sparsity.
|
NIPS/NeurIPS | 2000 | 59 |
| Entropy Numbers of Linear Function Classes.
|
COLT | 2000 | 20 |
| The Entropy Regularization Information Criterion.
|
NIPS/NeurIPS | 1999 | 3 |
| Support Vector Method for Novelty Detection.
|
NIPS/NeurIPS | 1999 | 1801 |
| Covering Numbers for Support Vector Machines.
|
COLT | 1999 | 74 |
| Shrinking the Tube: A New Support Vector Regression Algorithm.
|
NIPS/NeurIPS | 1998 | 217 |
| A PAC Analysis of a Bayesian Estimator.
|
COLT | 1997 | 173 |
| A Framework for Structural Risk Minimisation.
|
COLT | 1996 | 103 |
| The Importance of Convexity in Learning with Squared Loss.
|
COLT | 1996 | 0 |
| Existence and uniqueness results for neural network approximations.
|
IEEE Trans. Neural Networks | 1995 | 54 |
| On Efficient Agnostic Learning of Linear Combinations of Basis Functions.
|
COLT | 1995 | 20 |
| Online Learning via Congregational Gradient Descent.
|
COLT | 1995 | 11 |
| Examples of learning curves from a modified VC-formalism.
|
NIPS/NeurIPS | 1995 | 2 |
| Fat-Shattering and the Learnability of Real-Valued Functions.
|
COLT | 1994 | 158 |
| Lower Bounds on the VC-Dimension of Smoothly Parametrized Function Classes.
|
COLT | 1994 | 9 |
| Rational Parametrizations of Neural Networks.
|
NIPS/NeurIPS | 1992 | 1 |
| Investigating the Distribution Assumptions in the Pac Learning Model.
|
COLT | 1991 | 12 |
| Splines, Rational Functions and Neural Networks.
|
NIPS/NeurIPS | 1991 | 7 |
| epsilon-Entropy and the Complexity of Feedforward Neural Networks.
|
NIPS/NeurIPS | 1990 | 0 |