Learning tensors from partial binary measurements

1 code implementation • 31 Mar 2018 • Navid Ghadermarzy, Yaniv Plan, Ozgur Yilmaz

In this paper we generalize the 1-bit matrix completion problem to higher order tensors.

Statistics Theory Information Theory Information Theory Optimization and Control Statistics Theory 62B10, 94A17, 15A69, 62D05 H.3.3; I.2.6

Reinforcement Learning via Replica Stacking of Quantum Measurements for the Training of Quantum Boltzmann Machines

no code implementations • ICLR 2018 • Anna Levit,  Daniel Crawford, Navid Ghadermarzy, Jaspreet S. Oberoi, Ehsan Zahedinejad, Pooya Ronagh

The experimental results show that our technique is a promising method for harnessing the power of quantum sampling in reinforcement learning tasks.

reinforcement-learning Reinforcement Learning (RL)

Near-optimal sample complexity for convex tensor completion

1 code implementation • 14 Nov 2017 • Navid Ghadermarzy, Yaniv Plan, Özgür Yılmaz

In this paper, we show that by using an atomic-norm whose atoms are rank-$1$ sign tensors, one can obtain a sample complexity of $O(dN)$.

Free energy-based reinforcement learning using a quantum processor

1 code implementation • 29 May 2017 • Anna Levit, Daniel Crawford, Navid Ghadermarzy, Jaspreet S. Oberoi, Ehsan Zahedinejad, Pooya Ronagh

The experimental results show that our technique is a promising method for harnessing the power of quantum sampling in reinforcement learning tasks.

reinforcement-learning Reinforcement Learning (RL)

Reinforcement Learning Using Quantum Boltzmann Machines

no code implementations • 17 Dec 2016 • Daniel Crawford, Anna Levit, Navid Ghadermarzy, Jaspreet S. Oberoi, Pooya Ronagh

We investigate whether quantum annealers with select chip layouts can outperform classical computers in reinforcement learning tasks.

reinforcement-learning Reinforcement Learning (RL)