Search Results for author: Gavin Brown

Found 25 papers, 7 papers with code

Insufficient Statistics Perturbation: Stable Estimators for Private Least Squares

no code implementations23 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.

Private Gradient Descent for Linear Regression: Tighter Error Bounds and Instance-Specific Uncertainty Estimation

no code implementations21 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.

Metalearning with Very Few Samples Per Task

no code implementations21 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.

Binary Classification

A max-affine spline approximation of neural networks using the Legendre transform of a convex-concave representation

1 code implementation16 Jul 2023 Adam Perrett, Danny Wood, Gavin Brown

This work presents a novel algorithm for transforming a neural network into a spline representation.

Tiny Classifier Circuits: Evolving Accelerators for Tabular Data

no code implementations28 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.


Fast, Sample-Efficient, Affine-Invariant Private Mean and Covariance Estimation for Subgaussian Distributions

no code implementations28 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.

Open-Ended Question Answering

A Unified Theory of Diversity in Ensemble Learning

1 code implementation10 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.

Ensemble Learning Open-Ended Question Answering

Outlier detection of vital sign trajectories from COVID-19 patients

1 code implementation15 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.

Outlier Detection Time Series +1

Strong Memory Lower Bounds for Learning Natural Models

no code implementations9 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.

Bias-Variance Decompositions for Margin Losses

no code implementations26 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.

Covariance-Aware Private Mean Estimation Without Private Covariance Estimation

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.

When is Memorization of Irrelevant Training Data Necessary for High-Accuracy Learning?

1 code implementation11 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.


Performative Prediction in a Stateful World

1 code implementation8 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.

BIG-bench Machine Learning

Ensembles of Spiking Neural Networks

no code implementations15 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.

Ensemble Learning

Margin Maximization as Lossless Maximal Compression

1 code implementation28 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.

General Classification

Better Boosting with Bandits for Online Learning

no code implementations16 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.

To Ensemble or Not Ensemble: When does End-To-End Training Fail?

1 code implementation12 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?

Is feature selection secure against training data poisoning?

no code implementations21 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.

Computational Efficiency Data Poisoning +2

Minimax rates for cost-sensitive learning on manifolds with approximate nearest neighbours

no code implementations1 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.

General Classification

The K-Nearest Neighbour UCB algorithm for multi-armed bandits with covariates

no code implementations1 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.

Multi-Armed Bandits

Diversity and degrees of freedom in regression ensembles

no code implementations1 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.


Is Deep Learning Safe for Robot Vision? Adversarial Examples against the iCub Humanoid

no code implementations23 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.

General Classification

Modular Autoencoders for Ensemble Feature Extraction

no code implementations23 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.

ManTIME: Temporal expression identification and normalization in the TempEval-3 challenge

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.


Cannot find the paper you are looking for? You can Submit a new open access paper.