43 citations · 152 across the 7 of their papers we have counts for
7 papers
Quantifying Deep Learning Model Uncertainty in Conformal Prediction
Hamed Karimi, Reza Samavi
Precise estimation of predictive uncertainty in deep neural networks is a critical requirement for reliable decision-making in machine learning and statistical modeling, particular…
Effective optimization using sample persistence: A case study on quantum annealers and various Monte Carlo optimization methods
Hamed Karimi, Gili Rosenberg, Helmut G. Katzgraber
We present and apply a general-purpose, multi-start algorithm for improving the performance of low-energy samplers used for solving optimization problems. The algorithm iteratively…
Linear Convergence of Gradient and Proximal-Gradient Methods Under the Polyak-Łojasiewicz Condition
Hamed Karimi, Julie Nutini, Mark Schmidt
In 1963, Polyak proposed a simple condition that is sufficient to show a global linear convergence rate for gradient descent. This condition is a special case of the Łojasiewicz in…
Boosting quantum annealer performance via sample persistence
Hamed Karimi, Gili Rosenberg
We propose a novel method for reducing the number of variables in quadratic unconstrained binary optimization problems, using a quantum annealer (or any sampler) to fix the value o…
Logarithmic modes of critical gravity in de Sitter space-time
M. R. Setare, H. Karimi
In this paper we consider the critical gravity in four dimensional de Sitter space-time. We obtain logarithmic modes in the critical point of the theory. Then we show that these lo…
Towards a Rigorous Proof of Magnetism on the Edges of Graphene Nano-ribbons
Hamed Karimi, Ian Affleck
A zigzag edge of a graphene nanoribbon supports localized zero modes, ignoring interactions. Based mainly on mean field arguments and numerical approaches, it has been suggested th…