Search Results for author:
Found 25 papers, 7 papers with code
Insufficient Statistics Perturbation: Stable Estimators for Private Least Squares
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
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
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.
A max-affine spline approximation of neural networks using the Legendre transform of a convex-concave representation
This work presents a novel algorithm for transforming a neural network into a spline representation.
Tiny Classifier Circuits: Evolving Accelerators for Tabular Data
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
Our algorithm runs in time $\tilde{O}(nd^{\omega - 1} + nd/\varepsilon)$, where $\omega < 2. 38$ is the matrix multiplication exponent.
A Unified Theory of Diversity in Ensemble Learning
We present a theory of ensemble diversity, explaining the nature of diversity for a wide range of supervised learning scenarios.
Outlier detection of vital sign trajectories from COVID-19 patients
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.
Strong Memory Lower Bounds for Learning Natural Models
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
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
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?
Our problems are simple and fairly natural variants of the next-symbol prediction and the cluster labeling tasks.
Performative Prediction in a Stateful World
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.
Ensembles of Spiking Neural Networks
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.
Margin Maximization as Lossless Maximal Compression
The ultimate goal of a supervised learning algorithm is to produce models constructed on the training data that can generalize well to new examples.
Better Boosting with Bandits for Online Learning
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?
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?
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.
Diversity and degrees of freedom in regression ensembles
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.
The K-Nearest Neighbour UCB algorithm for multi-armed bandits with covariates
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.
Minimax rates for cost-sensitive learning on manifolds with approximate nearest neighbours
We study the approximate nearest neighbour method for cost-sensitive classification on low-dimensional manifolds embedded within a high-dimensional feature space.
Is Deep Learning Safe for Robot Vision? Adversarial Examples against the iCub Humanoid
Deep neural networks have been widely adopted in recent years, exhibiting impressive performances in several application domains.
Ranking Biomarkers Through Mutual Information
We study information theoretic methods for ranking biomarkers.
Modular Autoencoders for Ensemble Feature Extraction
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
This paper describes a temporal expression identification and normalization system, ManTIME, developed for the TempEval-3 challenge.
