Robert C. Williamson

177 papers A* 29A 1B 4C 1Misc 7Journal 96Unranked 36
YearRankTypeTitle / Venue / Authors
2025 J jnl
Aggregating Algorithm and Axiomatic Loss Aggregation.
Trans. Mach. Learn. Res.
Armando J. Cabrera Pacheco, Rabanus Derr, Robert C. Williamson
2025 J jnl
Geometry and Stability of Supervised Learning Problems.
J. Mach. Learn. Res.
Facundo Mémoli, Brantley Vose, Robert C. Williamson
2025 J jnl
Three Types of Calibration with Properties and their Semantic and Formal Relationships.
CoRR
Rabanus Derr, Jessie Finocchiaro, Robert C. Williamson
2024 J jnl
An Axiomatic Approach to Loss Aggregation and an Adapted Aggregating Algorithm.
CoRR
Armando J. Cabrera Pacheco, Rabanus Derr, Robert C. Williamson
2024 J jnl
Causal modelling without counterfactuals and individualised effects.
CoRR
Benedikt Höltgen, Robert C. Williamson
2024 J jnl
Five reasons against assuming a data-generating distribution in Machine Learning.
CoRR
Benedikt Höltgen, Robert C. Williamson
2024 J jnl
Four Facets of Forecast Felicity: Calibration, Predictiveness, Randomness and Regret.
CoRR
Rabanus Derr, Robert C. Williamson
2024 J jnl
Geometry and Stability of Supervised Learning Problems.
CoRR
Facundo Mémoli, Brantley Vose, Robert C. Williamson
2024 J jnl
Information Processing Equalities and the Information-Risk Bridge.
J. Mach. Learn. Res.
Robert C. Williamson, Zac Cranko
2024 — conf
Insights From Insurance for Fair Machine Learning.
FAccT
Christian Fröhlich, Robert C. Williamson
2024 J jnl
Limits to Predicting Online Speech Using Large Language Models.
CoRR
Mina Remeli, Moritz Hardt, Robert C. Williamson
2024 J jnl
Risk Measures and Upper Probabilities: Coherence and Stratification.
J. Mach. Learn. Res.
Christian Fröhlich, Robert C. Williamson
2024 J jnl
Scoring Rules and Calibration for Imprecise Probabilities.
CoRR
Christian Fröhlich, Robert C. Williamson
2024 J jnl
Strictly frequentist imprecise probability.
Int. J. Approx. Reason.
Christian Fröhlich, Rabanus Derr, Robert C. Williamson
2023 J jnl
A General Framework for Learning under Corruption: Label Noise, Attribute Noise, and Beyond.
CoRR
Laura Iacovissi, Nan Lu, Robert C. Williamson
2023 J jnl
Insights From Insurance for Fair Machine Learning: Responsibility, Performativity and Aggregates.
CoRR
Christian Fröhlich, Robert C. Williamson
2023 — conf
On the Richness of Calibration.
FAccT
Benedikt Höltgen, Robert C. Williamson
2023 J jnl
On the Richness of Calibration.
CoRR
Benedikt Höltgen, Robert C. Williamson
2023 A* conf
Random Classification Noise does not defeat All Convex Potential Boosters Irrespective of Model Choice.
ICML
Yishay Mansour, Richard Nock, Robert C. Williamson
2023 J jnl
Systems of Precision: Coherent Probabilities on Pre-Dynkin Systems and Coherent Previsions on Linear Subspaces.
Entropy
Rabanus Derr, Robert C. Williamson
2023 J jnl
Tailoring to the Tails: Risk Measures for Fine-Grained Tail Sensitivity.
Trans. Mach. Learn. Res.
Christian Fröhlich, Robert C. Williamson
2023 J jnl
The Geometry and Calculus of Losses.
J. Mach. Learn. Res.
Robert C. Williamson, Zac Cranko
2023 J jnl
The Geometry of Mixability.
CoRR
Armando J. Cabrera Pacheco, Robert C. Williamson
2023 J jnl
The Geometry of Mixability.
Trans. Mach. Learn. Res.
Armando J. Cabrera Pacheco, Robert C. Williamson
2023 — conf
The set structure of precision.
ISIPTA
Rabanus Derr, Robert C. Williamson
2023 — conf
Towards a strictly frequentist theory of imprecise probability.
ISIPTA
Christian Fröhlich, Rabanus Derr, Robert C. Williamson
2022 J jnl
Assessing AI Fairness in Finance.
Computer
Lachlan McCalman, Daniel Steinberg, Grace Abuhamad, Marc-Etienne Brunet, Robert C. Williamson, Richard S. Zemel
2022 J jnl
Fairness and Randomness in Machine Learning: Statistical Independence and Relativization.
CoRR
Rabanus Derr, Robert C. Williamson
2022 J jnl
Information Processing Equalities and the Information-Risk Bridge.
CoRR
Robert C. Williamson, Zac Cranko
2022 J jnl
Risk Measures and Upper Probabilities: Coherence and Stratification.
CoRR
Christian Fröhlich, Robert C. Williamson
2022 J jnl
Tailoring to the Tails: Risk Measures for Fine-Grained Tail Sensitivity.
CoRR
Christian Fröhlich, Robert C. Williamson
2022 J jnl
The Geometry and Calculus of Losses.
CoRR
Robert C. Williamson, Zac Cranko
2022 J jnl
What killed the Convex Booster ?
CoRR
Yishay Mansour, Richard Nock, Robert C. Williamson
2020 A* conf
PAC-Bayesian Bound for the Conditional Value at Risk.
NeurIPS
Zakaria Mhammedi, Benjamin Guedj, Robert C. Williamson
2020 J jnl
PAC-Bayesian Bound for the Conditional Value at Risk.
CoRR
Zakaria Mhammedi, Benjamin Guedj, Robert C. Williamson
2019 A* conf
A Primal-Dual link between GANs and Autoencoders.
NeurIPS
Hisham Husain, Richard Nock, Robert C. Williamson
2019 J jnl
Adversarial Networks and Autoencoders: The Primal-Dual Relationship and Generalization Bounds.
CoRR
Hisham Husain, Richard Nock, Robert C. Williamson
2019 C conf
Costs and Benefits of Fair Representation Learning.
AIES
Daniel McNamara, Cheng Soon Ong, Robert C. Williamson
2019 A* conf
Fairness risk measures.
ICML
Robert C. Williamson, Aditya Krishna Menon
2019 J jnl
Fairness risk measures.
CoRR
Robert C. Williamson, Aditya Krishna Menon
2019 A* conf
Lossless or Quantized Boosting with Integer Arithmetic.
ICML
Richard Nock, Robert C. Williamson
2018 A* conf
Constant Regret, Generalized Mixability, and Mirror Descent.
NeurIPS
Zakaria Mhammedi, Robert C. Williamson
2018 J jnl
Constant Regret, Generalized Mixability, and Mirror Descent.
CoRR
Zakaria Mhammedi, Robert C. Williamson
2018 J jnl
Exp-Concavity of Proper Composite Losses.
CoRR
Parameswaran Kamalaruban, Robert C. Williamson, Xinhua Zhang
2018 J jnl
Minimax Lower Bounds for Cost Sensitive Classification.
CoRR
Parameswaran Kamalaruban, Robert C. Williamson
2018 — conf
The cost of fairness in binary classification.
FAT
Aditya Krishna Menon, Robert C. Williamson
2017 J jnl
A Theory of Learning with Corrupted Labels.
J. Mach. Learn. Res.
Brendan van Rooyen, Robert C. Williamson
2017 J jnl
Provably Fair Representations.
CoRR
Daniel McNamara, Cheng Soon Ong, Robert C. Williamson
2017 J jnl
The cost of fairness in classification.
CoRR
Aditya Krishna Menon, Robert C. Williamson
2017 — conf
f-GANs in an Information Geometric Nutshell.
NIPS
Richard Nock, Zac Cranko, Aditya Krishna Menon, Lizhen Qu, Robert C. Williamson
2017 J jnl
f-GANs in an Information Geometric Nutshell.
CoRR
Richard Nock, Zac Cranko, Aditya Krishna Menon, Lizhen Qu, Robert C. Williamson
2016 J jnl
A Modular Theory of Feature Learning.
CoRR
Daniel McNamara, Cheng Soon Ong, Robert C. Williamson
2016 J jnl
Bipartite Ranking: a Risk-Theoretic Perspective.
J. Mach. Learn. Res.
Aditya Krishna Menon, Robert C. Williamson
2016 J jnl
Composite Multiclass Losses.
J. Mach. Learn. Res.
Robert C. Williamson, Elodie Vernet, Mark D. Reid
2015 J jnl
A Theory of Feature Learning.
CoRR
Brendan van Rooyen, Robert C. Williamson
2015 A* conf
Exp-Concavity of Proper Composite Losses.
COLT
Parameswaran Kamalaruban, Robert C. Williamson, Xinhua Zhang
2015 J jnl
Fast rates in statistical and online learning.
CoRR
Tim van Erven, Peter D. Grünwald, Nishant A. Mehta, Mark D. Reid, Robert C. Williamson
2015 J jnl
Fast rates in statistical and online learning.
J. Mach. Learn. Res.
Tim van Erven, Peter D. Grünwald, Nishant A. Mehta, Mark D. Reid, Robert C. Williamson
2015 A* conf
Generalized Mixability via Entropic Duality.
COLT
Mark D. Reid, Rafael M. Frongillo, Robert C. Williamson, Nishant A. Mehta
2015 J jnl
Learning in the Presence of Corruption.
CoRR
Brendan van Rooyen, Robert C. Williamson
2015 — conf
Learning with Symmetric Label Noise: The Importance of Being Unhinged.
NIPS
Brendan van Rooyen, Aditya Krishna Menon, Robert C. Williamson
2015 J jnl
Learning with Symmetric Label Noise: The Importance of Being Unhinged.
CoRR
Brendan van Rooyen, Aditya Krishna Menon, Robert C. Williamson
2014 A* conf
Bayes-Optimal Scorers for Bipartite Ranking.
COLT
Aditya Krishna Menon, Robert C. Williamson
2014 A* conf
Elicitation and Identification of Properties.
COLT
Ingo Steinwart, Chloé Pasin, Robert C. Williamson, Siyu Zhang
2014 — conf
From Stochastic Mixability to Fast Rates.
NIPS
Nishant A. Mehta, Robert C. Williamson
2014 J jnl
From Stochastic Mixability to Fast Rates.
CoRR
Nishant A. Mehta, Robert C. Williamson
2014 J jnl
Generalised Mixability, Constant Regret, and Bayesian Updating.
CoRR
Mark D. Reid, Rafael M. Frongillo, Robert C. Williamson
2014 J jnl
Generalized Mixability via Entropic Duality.
CoRR
Mark D. Reid, Rafael M. Frongillo, Robert C. Williamson, Nishant A. Mehta
2014 A* conf
On the Consistency of Output Code Based Learning Algorithms for Multiclass Learning Problems.
COLT
Harish G. Ramaswamy, Balaji Srinivasan Babu, Shivani Agarwal, Robert C. Williamson
2014 A* conf
The Geometry of Losses.
COLT
Robert C. Williamson
2013 — conf
Loss Functions.
Empirical Inference
Robert C. Williamson
2012 A* ed.
COLT 2012 - The 25th Annual Conference on Learning Theory, June 25-27, 2012, Edinburgh, Scotland
COLT
Shie Mannor, Nathan Srebro, Robert C. Williamson
2012 — conf
Clustering: Science or Art?
ICML Unsupervised and Transfer Learning
Ulrike von Luxburg, Robert C. Williamson, Isabelle Guyon
2012 A* conf
Divergences and Risks for Multiclass Experiments.
COLT
Dario García-García, Robert C. Williamson
2012 — conf
Mixability in Statistical Learning.
NIPS
Tim van Erven, Peter D. Grünwald, Mark D. Reid, Robert C. Williamson
2012 J jnl
Mixability is Bayes Risk Curvature Relative to Log Loss.
J. Mach. Learn. Res.
Tim van Erven, Mark D. Reid, Robert C. Williamson
2012 J jnl
Strategy-Proof Prediction Markets
CoRR
Ayman Ghoneim, Robert C. Williamson
2012 J jnl
The Convexity and Design of Composite Multiclass Losses
CoRR
Mark D. Reid, Robert C. Williamson, Peng Sun
2012 A* conf
The Convexity and Design of Composite Multiclass Losses.
ICML
Mark D. Reid, Robert C. Williamson, Peng Sun
2011 — conf
Composite Multiclass Losses.
NIPS
Elodie Vernet, Robert C. Williamson, Mark D. Reid
2011 J jnl
Information, Divergence and Risk for Binary Experiments.
J. Mach. Learn. Res.
Mark D. Reid, Robert C. Williamson
2011 A* conf
Mixability is Bayes Risk Curvature Relative to Log Loss.
COLT
Tim van Erven, Mark D. Reid, Robert C. Williamson
2010 J jnl
Composite Binary Losses.
J. Mach. Learn. Res.
Mark D. Reid, Robert C. Williamson
2010 A conf
Convexity of Proper Composite Binary Losses.
AISTATS
Mark D. Reid, Robert C. Williamson
2009 J jnl
Generalised Pinsker Inequalities
CoRR
Mark D. Reid, Robert C. Williamson
2009 A* conf
Generalised Pinsker Inequalities.
COLT
Mark D. Reid, Robert C. Williamson
2009 A* conf
Surrogate regret bounds for proper losses.
ICML
Mark D. Reid, Robert C. Williamson
2008 J jnl
Correction to "The Importance of Convexity in Learning With Squared Loss".
IEEE Trans. Inf. Theory
Wee Sun Lee, Peter L. Bartlett, Robert C. Williamson
2007 J jnl
The Need for Open Source Software in Machine Learning.
J. Mach. Learn. Res.
Sören Sonnenburg, Mikio L. Braun, Cheng Soon Ong, Samy Bengio, Léon Bottou, Geoffrey Holmes, Yann LeCun, Klaus-Robert Müller, Fernando Pereira, Carl Edward Rasmussen, Gunnar Rätsch, Bernhard Schölkopf, Alexander J. Smola, Pascal Vincent, Jason Weston, Robert C. Williamson
2006 J jnl
Particle Filter Design Using Importance Sampling for Acoustic Source Localisation and Tracking in Reverberant Environments.
EURASIP J. Adv. Signal Process.
Eric A. Lehmann, Robert C. Williamson
2005 B conf
Learnability of Probabilistic Automata via Oracles.
ALT
Omri Guttman, S. V. N. Vishwanathan, Robert C. Williamson
2005 J jnl
Learning the Kernel with Hyperkernels.
J. Mach. Learn. Res.
Cheng Soon Ong, Alexander J. Smola, Robert C. Williamson
2004 J jnl
Online learning with kernels.
IEEE Trans. Signal Process.
Jyrki Kivinen, Alexander J. Smola, Robert C. Williamson
2003 — conf
Acoustic beamforming exploiting directionality of human speech sources.
ICASSP (5)
Terence Betlehem, Robert C. Williamson
2003 — conf
Channel equalization and the Bayes point machine.
ICASSP (4)
Edward Harrington, Jyrki Kivinen, Robert C. Williamson
2003 — conf
Experimental comparison of particle filtering algorithms for acoustic source localization in a reverberant room.
ICASSP (5)
Eric A. Lehmann, Darren B. Ward, Robert C. Williamson
2003 B conf
Loop removal from LDPC codes.
ITW
James A. McGowan, Robert C. Williamson
2003 B conf
Online Bayes Point Machines.
PAKDD
Edward Harrington, Ralf Herbrich, Jyrki Kivinen, John C. Platt, Robert C. Williamson
2003 J jnl
Particle filtering algorithms for tracking an acoustic source in a reverberant environment.
IEEE Trans. Speech Audio Process.
Darren B. Ward, Eric A. Lehmann, Robert C. Williamson
2002 A* conf
Agnostic Learning Nonconvex Function Classes.
COLT
Shahar Mendelson, Robert C. Williamson
2002 J jnl
Algorithmic Luckiness.
J. Mach. Learn. Res.
Ralf Herbrich, Robert C. Williamson
2002 J jnl
Covering numbers for support vector machines.
IEEE Trans. Inf. Theory
Ying Guo, Peter L. Bartlett, John Shawe-Taylor, Robert C. Williamson
2002 J jnl
Exploiting sparsity in adaptive filters.
IEEE Trans. Signal Process.
Richard K. Martin, William A. Sethares, Robert C. Williamson, C. Richard Johnson Jr.
2002 — conf
Hyperkernels.
NIPS
Cheng Soon Ong, Alexander J. Smola, Robert C. Williamson
2002 B conf
Large Margin Classification for Moving Targets.
ALT
Jyrki Kivinen, Alexander J. Smola, Robert C. Williamson
2002 Misc conf
Particle filter beamforming for acoustic source localization in a reverberant environment.
ICASSP
Darren B. Ward, Robert C. Williamson
2001 — conf
Algorithmic Luckiness.
NIPS
Ralf Herbrich, Robert C. Williamson
2001 — ed.
Computational Learning Theory, 14th Annual Conference on Computational Learning Theory, COLT 2001 and 5th European Conference on Computational Learning Theory, EuroCOLT 2001, Amsterdam, The Netherlands, July 16-19, 2001, Proceedings
COLT/EuroCOLT
David P. Helmbold, Robert C. Williamson
2001 — ch.
Constant Directivity Beamforming.
Microphone Arrays
Darren B. Ward, Rodney A. Kennedy, Robert C. Williamson
2001 J jnl
Convergence of exponentiated gradient algorithms.
IEEE Trans. Signal Process.
Simon I. Hill, Robert C. Williamson
2001 J jnl
Estimating the Support of a High-Dimensional Distribution.
Neural Comput.
Bernhard Schölkopf, John C. Platt, John Shawe-Taylor, Alexander J. Smola, Robert C. Williamson
2001 J jnl
Generalization performance of regularization networks and support vector machines via entropy numbers of compact operators.
IEEE Trans. Inf. Theory
Robert C. Williamson, Alexander J. Smola, Bernhard Schölkopf
2001 — conf
Kernel Machines and Boolean Functions.
NIPS
Adam Kowalczyk, Alexander J. Smola, Robert C. Williamson
2001 — conf
Online Learning with Kernels.
NIPS
Jyrki Kivinen, Alexander J. Smola, Robert C. Williamson
2001 J jnl
Prior Knowledge and Preferential Structures in Gradient Descent Learning Algorithms.
J. Mach. Learn. Res.
Robert E. Mahony, Robert C. Williamson
2001 J jnl
Regularized Principal Manifolds.
J. Mach. Learn. Res.
Alexander J. Smola, Sebastian Mika, Bernhard Schölkopf, Robert C. Williamson
2001 — conf
Very low voltage power conversion.
ISCAS (3)
Marshall Shepard, Robert C. Williamson
2000 A* conf
Entropy Numbers of Linear Function Classes.
COLT
Robert C. Williamson, Alexander J. Smola, Bernhard Schölkopf
2000 J jnl
Equalization in an acoustic reverberant environment: robustness results.
IEEE Trans. Speech Audio Process.
Biljana D. Radlovic, Robert C. Williamson, Rodney A. Kennedy
2000 Misc conf
Error performance of a channel of known impulse response.
ICASSP
Paul D. Teal, Robert C. Williamson, Rodney A. Kennedy
2000 — conf
From Margin to Sparsity.
NIPS
Thore Graepel, Ralf Herbrich, Robert C. Williamson
2000 J jnl
New Support Vector Algorithms.
Neural Comput.
Bernhard Schölkopf, Alexander J. Smola, Robert C. Williamson, Peter L. Bartlett
2000 — conf
Regularization with Dot-Product Kernels.
NIPS
Alexander J. Smola, Zoltán L. Óvári, Robert C. Williamson
1999 — conf
An analysis of the exponentiated gradient descent algorithm.
ISSPA
Simon I. Hill, Robert C. Williamson
1999 — conf
Beamforming for a source located in the interior of a sensor array.
ISSPA
Darren B. Ward, Robert C. Williamson
1999 A* conf
Covering Numbers for Support Vector Machines.
COLT
Ying Guo, Peter L. Bartlett, John Shawe-Taylor, Robert C. Williamson
1999 — conf
Entropy Numbers, Operators and Support Vector Kernels.
EuroCOLT
Robert C. Williamson, Alexander J. Smola, Bernhard Schölkopf
1999 J jnl
Finite sample properties of linear model identification.
IEEE Trans. Autom. Control.
Erik Weyer, Robert C. Williamson, Iven M. Y. Mareels
1999 — conf
Nearfield broadband adaptive beamforming.
ISSPA
Thushara D. Abhayapala, Rodney A. Kennedy, Robert C. Williamson, Darren B. Ward
1999 J jnl
Noise modeling for nearfield array optimization.
IEEE Signal Process. Lett.
Thushara D. Abhayapala, Rodney A. Kennedy, Robert C. Williamson
1999 Misc conf
On the poor robustness of sound equalization in reverberant environments.
ICASSP
Biljana D. Radlovic, Robert C. Williamson, Rodney A. Kennedy
1999 — conf
Regularized Principal Manifolds.
EuroCOLT
Alexander J. Smola, Robert C. Williamson, Sebastian Mika, Bernhard Schölkopf
1999 — conf
Support Vector Method for Novelty Detection.
NIPS
Bernhard Schölkopf, Robert C. Williamson, Alexander J. Smola, John Shawe-Taylor, John C. Platt
1999 — conf
The Entropy Regularization Information Criterion.
NIPS
Alexander J. Smola, John Shawe-Taylor, Bernhard Schölkopf, Robert C. Williamson
1998 Misc conf
Broadband beamforming using elementary shape invariant beampatterns.
ICASSP
Thushara D. Abhayapala, Rodney A. Kennedy, Robert C. Williamson
1998 J jnl
On the Relationship Between Behavioural and Standard Methods for System Identification.
Autom.
Erik Weyer, Robert C. Williamson, Iven M. Y. Mareels
1998 — conf
Shrinking the Tube: A New Support Vector Regression Algorithm.
NIPS
Bernhard Schölkopf, Peter L. Bartlett, Alexander J. Smola, Robert C. Williamson
1998 J jnl
Structural Risk Minimization Over Data-Dependent Hierarchies.
IEEE Trans. Inf. Theory
John Shawe-Taylor, Peter L. Bartlett, Robert C. Williamson, Martin Anthony
1998 J jnl
The Importance of Convexity in Learning with Squared Loss.
IEEE Trans. Inf. Theory
Wee Sun Lee, Peter L. Bartlett, Robert C. Williamson
1997 A* conf
A PAC Analysis of a Bayesian Estimator.
COLT
John Shawe-Taylor, Robert C. Williamson
1997 Misc conf
An adaptive algorithm for broadband frequency invariant beamforming.
ICASSP
Darren B. Ward, Rodney A. Kennedy, Robert C. Williamson
1997 J jnl
Correction to 'Lower Bounds on the VC-Dimension of Smoothly Parametrized Function Classes'.
Neural Comput.
Wee Sun Lee, Peter L. Bartlett, Robert C. Williamson
1997 J jnl
Decision region approximation by polynomials or neural networks.
IEEE Trans. Inf. Theory
Kim L. Blackmore, Robert C. Williamson, Iven M. Y. Mareels
1997 J jnl
Online learning via congregational gradient descent.
Math. Control. Signals Syst.
Kim L. Blackmore, Robert C. Williamson, Iven M. Y. Mareels, William A. Sethares
1997 J jnl
Sampling rate versus quantisation in speech coders.
Signal Process.
Jennifer A. Fulton, Robert R. Bitmead, Robert C. Williamson
1996 A* conf
A Framework for Structural Risk Minimisation.
COLT
John Shawe-Taylor, Peter L. Bartlett, Robert C. Williamson, Martin Anthony
1996 J jnl
Efficient agnostic learning of neural networks with bounded fan-in.
IEEE Trans. Inf. Theory
Wee Sun Lee, Peter L. Bartlett, Robert C. Williamson
1996 J jnl
FIR filter design for frequency invariant beamformers.
IEEE Signal Process. Lett.
Darren B. Ward, Rodney A. Kennedy, Robert C. Williamson
1996 J jnl
Fat-Shattering and the Learnability of Real-Valued Functions.
J. Comput. Syst. Sci.
Peter L. Bartlett, Philip M. Long, Robert C. Williamson
1996 Misc conf
Nearfield broadband frequency invariant beamforming.
ICASSP
Rodney A. Kennedy, Thushara D. Abhayapala, Darren B. Ward, Robert C. Williamson
1996 A* conf
The Importance of Convexity in Learning with Squared Loss.
COLT
Wee Sun Lee, Peter L. Bartlett, Robert C. Williamson
1996 J jnl
The VC Dimension and Pseudodimension of Two-Layer Neural Networks with Discrete Inputs.
Neural Comput.
Peter L. Bartlett, Robert C. Williamson
1995 J jnl
An efficient calculation of the moments of matched and mismatched hidden Markov models.
IEEE Trans. Signal Process.
Mehmet Karan, Brian D. O. Anderson, Robert C. Williamson
1995 J jnl
Characterization of threshold for single tone maximum likelihood frequency estimation.
IEEE Trans. Signal Process.
Ben James, Brian D. O. Anderson, Robert C. Williamson
1995 — conf
Examples of learning curves from a modified VC-formalism.
NIPS
Adam Kowalczyk, Jacek Szymanski, Peter L. Bartlett, Robert C. Williamson
1995 J jnl
Existence and uniqueness results for neural network approximations.
IEEE Trans. Neural Networks
Robert C. Williamson, Uwe Helmke
1995 — conf
Learning curves from a modified VC-formalism: a case study.
ICNN
Adam Kowalczyk, J. Szymariski, Robert C. Williamson
1995 J jnl
Lower Bounds on the VC Dimension of Smoothly Parameterized Function Classes.
Neural Comput.
Wee Sun Lee, Peter L. Bartlett, Robert C. Williamson
1995 J jnl
Neural networks, rational functions, and realization theory.
Math. Control. Signals Syst.
Uwe Helmke, Robert C. Williamson
1995 A* conf
On Efficient Agnostic Learning of Linear Combinations of Basis Functions.
COLT
Wee Sun Lee, Peter L. Bartlett, Robert C. Williamson
1995 A* conf
Online Learning via Congregational Gradient Descent.
COLT
Kim L. Blackmore, Robert C. Williamson, Iven M. Y. Mareels, William A. Sethares
1994 — conf
A simple calculation of the joint moments of hidden Markov models.
ICASSP (4)
Mehmet Karan, Brian D. O. Anderson, Robert C. Williamson
1994 J jnl
Conditional mean and maximum likelihood approaches to multiharmonic frequency estimation.
IEEE Trans. Signal Process.
Ben James, Brian D. O. Anderson, Robert C. Williamson
1994 A* conf
Fat-Shattering and the Learnability of Real-Valued Functions.
COLT
Peter L. Bartlett, Philip M. Long, Robert C. Williamson
1994 A* conf
Lower Bounds on the VC-Dimension of Smoothly Parametrized Function Classes.
COLT
Wee Sun Lee, Peter L. Bartlett, Robert C. Williamson
1994 J jnl
Performance of the maximum likelihood constant frequency estimator for frequency tracking.
IEEE Trans. Signal Process.
Mehmet Karan, Robert C. Williamson, Brian D. O. Anderson
1994 J jnl
Threshold effects in multiharmonic maximum likelihood frequency estimation.
Signal Process.
Robert C. Williamson, Ben James, Brian D. O. Anderson, Peter J. Kootsookos
1993 J jnl
The relationship between instantaneous frequency and time-frequency representations.
IEEE Trans. Signal Process.
Brian C. Lovell, Robert C. Williamson, Boualem Boashash
1992 — conf
Rational Parametrizations of Neural Networks.
NIPS
Uwe Helmke, Robert C. Williamson
1992 J jnl
The statistical performance of some instantaneous frequency estimators.
IEEE Trans. Signal Process.
Brian C. Lovell, Robert C. Williamson
1991 J jnl
An extreme limit theorem for dependency bounds of normalized sums of random variables.
Inf. Sci.
Robert C. Williamson
1991 A* conf
Investigating the Distribution Assumptions in the Pac Learning Model.
COLT
Peter L. Bartlett, Robert C. Williamson
1991 — conf
Splines, Rational Functions and Neural Networks.
NIPS
Robert C. Williamson, Peter L. Bartlett
1991 Misc conf
The circular nature of discrete-time frequency estimates.
ICASSP
Brian C. Lovell, Peter J. Kootsookos, Robert C. Williamson
1990 — —
Probabilistic arithmetic
Robert C. Williamson
1990 J jnl
Probabilistic arithmetic. I. Numerical methods for calculating convolutions and dependency bounds.
Int. J. Approx. Reason.
Robert C. Williamson, Tom Downs
1990 — conf
epsilon-Entropy and the Complexity of Feedforward Neural Networks.
NIPS
Robert C. Williamson