no code implementations • 23 Apr 2024 • Gavin Brown, Jonathan Hayase, Samuel Hopkins, Weihao Kong, Xiyang Liu, Sewoong Oh, Juan C. Perdomo, Adam Smith
We present a sample- and time-efficient differentially private algorithm for ordinary least squares, with error that depends linearly on the dimension and is independent of the condition number of $X^\top X$, where $X$ is the design matrix.
no code implementations • 21 Feb 2024 • Gavin Brown, Krishnamurthy Dvijotham, Georgina Evans, Daogao Liu, Adam Smith, Abhradeep Thakurta
We provide an improved analysis of standard differentially private gradient descent for linear regression under the squared error loss.
no code implementations • 21 Dec 2023 • Maryam Aliakbarpour, Konstantina Bairaktari, Gavin Brown, Adam Smith, Nathan Srebro, Jonathan Ullman
In multitask learning, we are given a fixed set of related learning tasks and need to output one accurate model per task, whereas in metalearning we are given tasks that are drawn i. i. d.
1 code implementation • 16 Jul 2023 • Adam Perrett, Danny Wood, Gavin Brown
This work presents a novel algorithm for transforming a neural network into a spline representation.
no code implementations • 28 Feb 2023 • Konstantinos Iordanou, Timothy Atkinson, Emre Ozer, Jedrzej Kufel, John Biggs, Gavin Brown, Mikel Lujan
This paper proposes a methodology for automatically generating predictor circuits for classification of tabular data with comparable prediction performance to conventional ML techniques while using substantially fewer hardware resources and power.
no code implementations • 28 Jan 2023 • Gavin Brown, Samuel B. Hopkins, Adam Smith
Our algorithm runs in time $\tilde{O}(nd^{\omega - 1} + nd/\varepsilon)$, where $\omega < 2. 38$ is the matrix multiplication exponent.
1 code implementation • 10 Jan 2023 • Danny Wood, Tingting Mu, Andrew Webb, Henry Reeve, Mikel Luján, Gavin Brown
We present a theory of ensemble diversity, explaining the nature of diversity for a wide range of supervised learning scenarios.
1 code implementation • 15 Jul 2022 • Sara Summerton, Ann Tivey, Rohan Shotton, Gavin Brown, Oliver C. Redfern, Rachel Oakley, John Radford, David C. Wong
In this work, we present a novel trajectory comparison algorithm to identify abnormal vital sign trends, with the aim of improving recognition of deteriorating health.
no code implementations • 9 Jun 2022 • Gavin Brown, Mark Bun, Adam Smith
We give lower bounds on the amount of memory required by one-pass streaming algorithms for solving several natural learning problems.
no code implementations • 26 Apr 2022 • Danny Wood, Tingting Mu, Gavin Brown
We introduce a novel bias-variance decomposition for a range of strictly convex margin losses, including the logistic loss (minimized by the classic LogitBoost algorithm), as well as the squared margin loss and canonical boosting loss.
no code implementations • NeurIPS 2021 • Gavin Brown, Marco Gaboardi, Adam Smith, Jonathan Ullman, Lydia Zakynthinou
Each of our estimators is based on a simple, general approach to designing differentially private mechanisms, but with novel technical steps to make the estimator private and sample-efficient.
1 code implementation • 11 Dec 2020 • Gavin Brown, Mark Bun, Vitaly Feldman, Adam Smith, Kunal Talwar
Our problems are simple and fairly natural variants of the next-symbol prediction and the cluster labeling tasks.
1 code implementation • 8 Nov 2020 • Gavin Brown, Shlomi Hod, Iden Kalemaj
We propose a theoretical framework where the response of a target population to the deployed classifier is modeled as a function of the classifier and the current state (distribution) of the population.
no code implementations • 15 Oct 2020 • Georgiana Neculae, Oliver Rhodes, Gavin Brown
The work demonstrates how ensembling can overcome the challenges of producing individual SNN models which can compete with traditional deep neural networks, and creates systems with fewer trainable parameters and smaller memory footprints, opening the door to low-power edge applications, e. g. implemented on neuromorphic hardware.
1 code implementation • 28 Jan 2020 • Nikolaos Nikolaou, Henry Reeve, Gavin Brown
The ultimate goal of a supervised learning algorithm is to produce models constructed on the training data that can generalize well to new examples.
no code implementations • 16 Jan 2020 • Nikolaos Nikolaou, Joseph Mellor, Nikunj C. Oza, Gavin Brown
The outputs of the ensemble need to be properly calibrated before they can be used as probability estimates.
1 code implementation • 12 Feb 2019 • Andrew M. Webb, Charles Reynolds, Wenlin Chen, Henry Reeve, Dan-Andrei Iliescu, Mikel Lujan, Gavin Brown
An interesting question is whether this trend will continue-are there any clear failure cases for E2E training?
no code implementations • 21 Apr 2018 • Huang Xiao, Battista Biggio, Gavin Brown, Giorgio Fumera, Claudia Eckert, Fabio Roli
Learning in adversarial settings is becoming an important task for application domains where attackers may inject malicious data into the training set to subvert normal operation of data-driven technologies.
no code implementations • 1 Mar 2018 • Henry WJ Reeve, Gavin Brown
We study the approximate nearest neighbour method for cost-sensitive classification on low-dimensional manifolds embedded within a high-dimensional feature space.
no code implementations • 1 Mar 2018 • Henry WJ Reeve, Gavin Brown
We provide an exact formula for the effective degrees of freedom in an NCL ensemble with fixed basis functions, showing that it is a continuous, convex and monotonically increasing function of the diversity parameter.
no code implementations • 1 Mar 2018 • Henry WJ Reeve, Joe Mellor, Gavin Brown
In addition, focusing on the case of bounded rewards, we give corresponding regret bounds for the k-Nearest Neighbour KL-UCB algorithm, which is an analogue of the KL-UCB algorithm adapted to the setting of multi-armed bandits with covariates.
no code implementations • 23 Aug 2017 • Marco Melis, Ambra Demontis, Battista Biggio, Gavin Brown, Giorgio Fumera, Fabio Roli
Deep neural networks have been widely adopted in recent years, exhibiting impressive performances in several application domains.
no code implementations • 5 Dec 2016 • Konstantinos Sechidis, Emily Turner, Paul D. Metcalfe, James Weatherall, Gavin Brown
We study information theoretic methods for ranking biomarkers.
no code implementations • 23 Nov 2015 • Henry W. J. Reeve, Gavin Brown
We introduce the concept of a Modular Autoencoder (MAE), capable of learning a set of diverse but complementary representations from unlabelled data, that can later be used for supervised tasks.
no code implementations • SEMEVAL 2013 • Michele Filannino, Gavin Brown, Goran Nenadic
This paper describes a temporal expression identification and normalization system, ManTIME, developed for the TempEval-3 challenge.