1 code implementation • 5 Nov 2017 • Tengyuan Liang, Tomaso Poggio, Alexander Rakhlin, James Stokes
We study the relationship between geometry and capacity measures for deep neural networks from an invariance viewpoint.
no code implementations • 16 Feb 2018 • Tengyuan Liang, James Stokes
Motivated by the pursuit of a systematic computational and algorithmic understanding of Generative Adversarial Networks (GANs), we present a simple yet unified non-asymptotic local convergence theory for smooth two-player games, which subsumes several discrete-time gradient-based saddle point dynamics.
no code implementations • 19 Feb 2019 • James Stokes, John Terilla
Inspired by the possibility that generative models based on quantum circuits can provide a useful inductive bias for sequence modeling tasks, we propose an efficient training algorithm for a subset of classically simulable quantum circuit models.
no code implementations • ICLR 2019 • Mingwei Wei, James Stokes, David J. Schwab
Batch Normalization (BatchNorm) is an extremely useful component of modern neural network architectures, enabling optimization using higher learning rates and achieving faster convergence.
2 code implementations • 4 Sep 2019 • James Stokes, Josh Izaac, Nathan Killoran, Giuseppe Carleo
A quantum generalization of Natural Gradient Descent is presented as part of a general-purpose optimization framework for variational quantum circuits.
1 code implementation • 9 May 2020 • Tianchen Zhao, Giuseppe Carleo, James Stokes, Shravan Veerapaneni
A notion of quantum natural evolution strategies is introduced, which provides a geometric synthesis of a number of known quantum/classical algorithms for performing classical black-box optimization.
no code implementations • 31 Jul 2020 • James Stokes, Javier Robledo Moreno, Eftychios A. Pnevmatikakis, Giuseppe Carleo
First-quantized deep neural network techniques are developed for analyzing strongly coupled fermionic systems on the lattice.
no code implementations • 20 Nov 2020 • Tianchen Zhao, James Stokes, Oliver Knitter, Brian Chen, Shravan Veerapaneni
An identification is found between meta-learning and the problem of determining the ground state of a randomly generated Hamiltonian drawn from a known ensemble.
no code implementations • 9 Dec 2020 • Di Luo, Giuseppe Carleo, Bryan K. Clark, James Stokes
Gauge symmetries play a key role in physics appearing in areas such as quantum field theories of the fundamental particles and emergent degrees of freedom in quantum materials.
1 code implementation • 15 Jul 2021 • James Stokes, Saibal De, Shravan Veerapaneni, Giuseppe Carleo
We initiate the study of neural-network quantum state algorithms for analyzing continuous-variable lattice quantum systems in first quantization.
no code implementations • 28 Mar 2022 • James Stokes, Brian Chen, Shravan Veerapaneni
This article aims to summarize recent and ongoing efforts to simulate continuous-variable quantum systems using flow-based variational quantum Monte Carlo techniques, focusing for pedagogical purposes on the example of bosons in the field amplitude (quadrature) basis.
no code implementations • 11 Aug 2022 • Tianchen Zhao, James Stokes, Shravan Veerapaneni
Variational optimization of neural-network representations of quantum states has been successfully applied to solve interacting fermionic problems.
no code implementations • 5 Nov 2022 • Oliver Knitter, James Stokes, Shravan Veerapaneni
Variational quantum algorithms (VQAs) utilize a hybrid quantum-classical architecture to recast problems of high-dimensional linear algebra as ones of stochastic optimization.
no code implementations • 6 Nov 2022 • Di Luo, Shunyue Yuan, James Stokes, Bryan K. Clark
Gauge Theory plays a crucial role in many areas in science, including high energy physics, condensed matter physics and quantum information science.