| 2024 | COLT | Insufficient Statistics Perturbation: Stable Estimators for Private Least Squares Extended Abstract. | Gavin Brown, Jonathan Hayase, Samuel B. Hopkins, Weihao Kong, Xiyang Liu, Sewoong Oh, Juan C. Perdomo, Adam Smith |
| 2024 | COLT | Metalearning with Very Few Samples Per Task. | Maryam Aliakbarpour, Konstantina Bairaktari, Gavin Brown, Adam Smith, Nathan Srebro, Jonathan R. Ullman |
| 2024 | FCCM | FINESSD: Near-Storage Feature Selection with Mutual Information for Resource-Limited FPGAs. | Nikolaos Kyparissas, Gavin Brown, Mikel Lujn |
| 2024 | ICML | Private Gradient Descent for Linear Regression: Tighter Error Bounds and Instance-Specific Uncertainty Estimation. | Gavin Brown, Krishnamurthy Dj Dvijotham, Georgina Evans, Daogao Liu, Adam Smith, Abhradeep Guha Thakurta |
| 2023 | COLT | Fast, Sample-Efficient, Affine-Invariant Private Mean and Covariance Estimation for Subgaussian Distributions. | Gavin Brown, Samuel B. Hopkins, Adam Smith |
| 2022 | AAAI | EnnCore: End-to-End Conceptual Guarding of Neural Architectures. | Edoardo Manino, Danilo S. Carvalho, Yi Dong, Julia Rozanova, Xidan Song, Mustafa A. Mustafa, Andr Freitas, Gavin Brown, Mikel Lujn, Xiaowei Huang, Lucas C. Cordeiro |
| 2022 | AISTATS | Performative Prediction in a Stateful World. | Gavin Brown, Shlomi Hod, Iden Kalemaj |
| 2022 | AISTATS | Bias-Variance Decompositions for Margin Losses. | Danny Wood, Tingting Mu, Gavin Brown |
| 2022 | COLT | Strong Memory Lower Bounds for Learning Natural Models. | Gavin Brown, Mark Bun, Adam D. Smith |
| 2021 | ICMLA | Mixed Spatio-Temporal Neural Networks on Real-time Prediction of Crimes. | Xiao Zhou, Xiao Wang, Gavin Brown, Chengchen Wang, Peter Chin |
| 2021 | STOC | When is memorization of irrelevant training data necessary for high-accuracy learning? | Gavin Brown, Mark Bun, Vitaly Feldman, Adam D. Smith, Kunal Talwar |
| 2018 | ALT | The K-Nearest Neighbour UCB Algorithm for Multi-Armed Bandits with Covariates. | Henry W. J. Reeve, Joe Mellor, Gavin Brown |
| 2017 | ALT | Minimax rates for cost-sensitive learning on manifolds with approximate nearest neighbours. | Henry W. J. Reeve, Gavin Brown |
| 2017 | ESANN | Mutual information for improving the efficiency of the SCH algorithm. | Diego Fernndez-Francos, Oscar Fontenla-Romero, Amparo Alonso-Betanzos, Gavin Brown |
| 2017 | ESANN | Degrees of Freedom in Regression Ensembles. | Henry W. J. Reeve, Gavin Brown |
| 2017 | IBPRIA | On the Use of Spearman's Rho to Measure the Stability of Feature Rankings. | Sarah Nogueira, Konstantinos Sechidis, Gavin Brown |
| 2017 | IJCNN | Exploring the consequences of distributed feature selection in DNA microarray data. | Vernica Boln-Canedo, Konstantinos Sechidis, Noelia Snchez-Maroo, Amparo Alonso-Betanzos, Gavin Brown |
| 2015 | ICML | Is Feature Selection Secure against Training Data Poisoning? | Huang Xiao, Battista Biggio, Gavin Brown, Giorgio Fumera, Claudia Eckert, Fabio Roli |
| 2014 | KR | Predicting Performance of OWL Reasoners: Locally or Globally? | Viachaslau Sazonau, Uli Sattler, Gavin Brown |
| 2014 | SSPR | Information Theoretic Feature Selection in Multi-label Data through Composite Likelihood. | Konstantinos Sechidis, Nikolaos Nikolaou, Gavin Brown |
| 2011 | GECCO | Online, GA based mixture of experts: a probabilistic model of ucs. | Narayanan Unny Edakunni, Gavin Brown, Tim Kovacs |
| 2011 | GECCO | Accuracy exponentiation in UCS and its effect on voting margins. | Tim Kovacs, Narayanan Unny Edakunni, Gavin Brown |
| 2010 | EUROGP | Analytic Solutions to Differential Equations under Graph-Based Genetic Programming. | Tom Seaton, Gavin Brown, Julian F. Miller |
| 2009 | FUSION | Information Fusion based decision support via Hidden Markov Models and time series anomaly detection. | Jonathan Edward Barker, Richard John Green, Paul Thomas, Gavin Brown, David Salmond |
| 2009 | GECCO | Modeling UCS as a mixture of experts. | Narayanan Unny Edakunni, Tim Kovacs, Gavin Brown, James A. R. Marshall |
| 2007 | GECCO | UCSpv: principled voting in UCS rule populations. | Gavin Brown, Tim Kovacs, James A. R. Marshall |
| 2007 | GECCO | Bayesian estimation of rule accuracy in UCS. | James A. R. Marshall, Gavin Brown, Tim Kovacs |
| 2003 | ICML | The Use of the Ambiguity Decomposition in Neural Network Ensemble Learning Methods. | Gavin Brown, Jeremy L. Wyatt |