20 citations · 49 across the 10 of their papers we have counts for
10 papers
Sparse Gaussian Processes with Spherical Harmonic Features Revisited
Stefanos Eleftheriadis, Dominic Richards, James Hensman
We revisit the Gaussian process model with spherical harmonic features and study connections between the associated RKHS, its eigenstructure and deep models. Based on this, we intr…
Double Deep Q Networks for Sensor Management in Space Situational Awareness
Benedict Oakes, Dominic Richards, Jordi Barr +1
We present a novel Double Deep Q Network (DDQN) application to a sensor management problem in space situational awareness (SSA). Frequent launches of satellites into Earth orbit po…
Comparing Classes of Estimators: When does Gradient Descent Beat Ridge Regression in Linear Models?
Dominic Richards, Edgar Dobriban, Patrick Rebeschini
Methods for learning from data depend on various types of tuning parameters, such as penalization strength or step size. Since performance can depend strongly on these parameters,…
Stability & Generalisation of Gradient Descent for Shallow Neural Networks without the Neural Tangent Kernel
Dominic Richards, Ilja Kuzborskij
We revisit on-average algorithmic stability of GD for training overparameterised shallow neural networks and prove new generalisation and excess risk bounds without the NTK or PL a…
Learning with Gradient Descent and Weakly Convex Losses
Dominic Richards, Mike Rabbat
We study the learning performance of gradient descent when the empirical risk is weakly convex, namely, the smallest negative eigenvalue of the empirical risk's Hessian is bounded…
Decentralised Learning with Random Features and Distributed Gradient Descent
Dominic Richards, Patrick Rebeschini, Lorenzo Rosasco
We investigate the generalisation performance of Distributed Gradient Descent with Implicit Regularisation and Random Features in the homogenous setting where a network of agents a…
Asymptotics of Ridge (less) Regression under General Source Condition
Dominic Richards, Jaouad Mourtada, Lorenzo Rosasco
We analyze the prediction error of ridge regression in an asymptotic regime where the sample size and dimension go to infinity at a proportional rate. In particular, we consider th…
Distributed Machine Learning with Sparse Heterogeneous Data
Dominic Richards, Sahand N. Negahban, Patrick Rebeschini
Motivated by distributed machine learning settings such as Federated Learning, we consider the problem of fitting a statistical model across a distributed collection of heterogeneo…
Optimal Statistical Rates for Decentralised Non-Parametric Regression with Linear Speed-Up
Dominic Richards, Patrick Rebeschini
We analyse the learning performance of Distributed Gradient Descent in the context of multi-agent decentralised non-parametric regression with the square loss function when i.i.d.…
Graph-Dependent Implicit Regularisation for Distributed Stochastic Subgradient Descent
Dominic Richards, Patrick Rebeschini
We propose graph-dependent implicit regularisation strategies for distributed stochastic subgradient descent (Distributed SGD) for convex problems in multi-agent learning. Under th…