Michael K. Cohen — accepted AI-conference papers

2025

Can a Bayesian Oracle Prevent Harm from an Agent?

Yoshua Bengio, Michael K. Cohen, Nikolay Malkin, Matt MacDermott, Damiano Fornasiere, Pietro Greiner +1

UAI 2025

Is there a way to design powerful AI systems based on machine learning methods that would satisfy probabilistic safety guarantees? With the long-term goal of obtaining a probabilistic guarantee that would apply in every context, we consider estimating a context-dependent bound on the probability of

Cited by 0 Source ↗PDF ↗code ↗Scholar ↗

2025

RL, but don’t do anything I wouldn’t do

Michael K. Cohen, Marcus Hutter, Yoshua Bengio, Stuart Russell

UAI 2025

In reinforcement learning (RL), if the agent’s reward differs from the designers’ true utility, even only rarely, the state distribution resulting from the agent’s policy can be very bad, in theory and in practice. When RL policies would devolve into undesired behavior, a common countermeasure is KL

Cited by 0 Source ↗PDF ↗code ↗Scholar ↗

2022

Log-Linear-Time Gaussian Processes Using Binary Tree Kernels

Michael K. Cohen, Sam Daulton, Michael A Osborne

NeurIPS 2022accept

Gaussian processes (GPs) produce good probabilistic models of functions, but most GP kernels require $O((n+m)n^2)$ time, where $n$ is the number of data points and $m$ the number of predictive locations. We present a new kernel that allows for Gaussian process regression in $O((n+m)\log(n+m))$ time.…

Cited by 8 Source ↗PDF ↗code ↗Scholar ↗