6 papers
The Impact of Operational-Data Fidelity when Assessing Safety-Critical Autonomous-Vehicle Software
Kizito Salako, Rabiu Tsoho Muhammad
For safety-critical software, data from the software's operational past (e.g. a sequence of success and failure events experienced by the software) can provide strong statistical s…
Fixed-Point Characterisations of Extremal Distributions under Partial Distributional Constraints
Kizito Salako, Rabiu Tsoho Muhammad
We present a methodological framework for solving robust inference problems with partially specified distributions over measurable subsets of a parameter space. Partial specificati…
Constructive Proofs of Generalized Boole--Frechet Bounds: A Dynamic Programming Approach
Kizito Salako
Extensions of the Boole--Frechet inequalities give sharp bounds for the probabilities of compound events, particularly when only the probabilities of atomic events (that make up th…
Conservative Software Reliability Assessments Using Collections of Bayesian Inference Problems
Kizito Salako, Rabiu Tsoho Muhammad
When using Bayesian inference to support conservative software reliability assessments, it is useful to consider a collection of Bayesian inference problems, with the aim of determ…
Performance Comparisons of Reinforcement Learning Algorithms for Sequential Experimental Design
Yasir Zubayr Barlas, Kizito Salako
Recent developments in sequential experimental design look to construct a policy that can efficiently navigate the design space, in a way that maximises the expected information ga…
Derivative-based regularization for regression
Enrico Lopedoto, Maksim Shekhunov, Vitaly Aksenov +2
In this work, we introduce a novel approach to regularization in multivariable regression problems. Our regularizer, called DLoss, penalises differences between the model's derivat…