32 citations · 87 across the 16 of their papers we have counts for
5 papers · 1 filter
Thermodynamic Algorithms for Quadratic Programming
Patryk-Lipka Bartosik, Kaelan Donatella, Maxwell Aifer +4
Thermodynamic computing has emerged as a promising paradigm for accelerating computation by harnessing the thermalization properties of physical systems. This work introduces a nov…
Thermodynamic Bayesian Inference
Maxwell Aifer, Samuel Duffield, Kaelan Donatella +6
A fully Bayesian treatment of complicated predictive models (such as deep neural networks) would enable rigorous uncertainty quantification and the automation of higher-level tasks…
Scalable Bayesian Learning with posteriors
Samuel Duffield, Kaelan Donatella, Johnathan Chiu +2
Although theoretically compelling, Bayesian learning with modern machine learning models is computationally challenging since it requires approximating a high dimensional posterior…
Thermodynamic Natural Gradient Descent
Kaelan Donatella, Samuel Duffield, Maxwell Aifer +3
Second-order training methods have better convergence properties than gradient descent but are rarely used in practice for large-scale training due to their computational overhead.…
Error Mitigation for Thermodynamic Computing
Maxwell Aifer, Denis Melanson, Kaelan Donatella +3
While physics-based computing can offer speed and energy efficiency compared to digital computing, it also is subject to errors that must be mitigated. For example, many error miti…