A high-bias, low-variance introduction to Machine Learning for physicists (2018-03-23T00:00:00.000000Z)

TL;DR

The review begins by covering fundamental concepts in ML and modern statistics such as the bias-variance tradeoff, overfitting, regularization, generalization, and gradient descent before moving on to more advanced topics in both supervised and unsupervised learning.

Authors

Pankaj Mehta

2 papers

D. Schwab

3 papers

M. Bukov

1 papers

Ching-Hao Wang

1 papers

A. Day

1 papers

C. Richardson

1 papers

Charles K. Fisher

1 papers

TL;DR

Authors

References358 items

Statistical Mechanics: Entropy, Order Parameters, and Complexity

Variable Selection

The Minimum Environmental Perturbation Principle: A New Perspective on Niche Theory

Manipulation of Spin Dynamics by Deep Reinforcement Learning Agent.

Characterization of photoexcited states in the half-filled one-dimensional extended Hubbard model assisted by machine learning

Machine learning assisted measurement of local topological invariants

Machine Learning in Seismology: Turning Data into Insights

Machine learning determination of dynamical parameters: The Ising model case

Reconstructing quantum states with generative models

Thermodynamics and Feature Extraction by Machine Learning

Spin-qubit noise spectroscopy from randomized benchmarking by supervised learning

Reinforcement learning decoders for fault-tolerant quantum computation

Learning to inflate. A gradient ascent approach to random inflation

DeepCMB: Lensing Reconstruction of the Cosmic Microwave Background with Deep Neural Networks

Correlations in the shear flow of athermal amorphous solids: a principal component analysis

Identifying quantum phase transitions using artificial neural networks on experimental data

QCD or what?

Reinforcement learning for autonomous preparation of Floquet-engineered states: Inverting the quantum Kapitza oscillator

Machine Learning Nonlocal Correlations.

Ferromagnetic resonance in thin films studied via cross-validation of numerical solutions of the Smit-Beljers equation: Application to (Ga,Mn)As

Building Machines that Learn and Think Like People

Weapons of Math Destruction: How Big Data Increases Inequality and Threatens Democracy

Learning non-Higgsable gauge groups in 4D F-theory

Towards quantum machine learning with tensor networks

Glassy Phase of Optimal Quantum Control.

Supervised learning of time-independent Hamiltonians for gate design

Quantum Machine Learning in Feature Hilbert Spaces.

Batched quantum state exponentiation and quantum Hebbian learning

Comparing dynamics: deep neural networks versus glassy systems

Supervised learning approach for recognizing magnetic skyrmion phases

Measurement-based adaptation protocol with quantum reinforcement learning

Neural network operations and Susuki–Trotter evolution of neural network states

Universal quantum control through deep reinforcement learning

Machine learning of frustrated classical spin models (II): Kernel principal component analysis

Quantum circuit learning

Learning dynamic Boltzmann distributions as reduced models of spatial chemical kinetics.

Parameter diagnostics of phases and phase transition learning by neural networks

Automatic spin-chain learning to explore the quantum speed limit

Constructing exact representations of quantum many-body systems with deep neural networks

Advantages of versatile neural-network decoding for topological codes

Quantum annealing versus classical machine learning applied to a simplified computational biology problem

Deep neural decoders for near term fault-tolerant experiments

Inferring relevant features: from QFT to PCA

Reinforcement Learning with Neural Networks for Quantum Feedback

Taking gradients through experiments: LSTMs and memory proximal policy optimization for black-box quantum control

Visualizing Neural Network Developing Perturbation Theory

UMAP: Uniform Manifold Approximation and Projection for Dimension Reduction

Neural Network Renormalization Group

Scale-invariant Feature Extraction of Neural Network and Renormalization Group Flow

Deep convolutional neural networks for eigenvalue problems in mechanics

Machine learning action parameters in lattice quantum chromodynamics

General framework for constructing fast and near-optimal machine-learning-based decoder of the topological stabilizer codes

Applications of deep learning to relativistic hydrodynamics

Thermodynamics of Restricted Boltzmann Machines and Related Learning Dynamics

Self-learning Monte Carlo with deep neural networks

Learning relevant features of data with multi-scale tensor networks

Fast Interpolation-based t-SNE for Improved Visualization of Single-Cell RNA-Seq Data

Machine learning techniques for state recognition and auto-tuning in quantum dots

Information Perspective to Probabilistic Modeling: Boltzmann Machines versus Born Machines

Towards reduction of autocorrelation in HMC by machine learning

Learning free energy landscapes using artificial neural networks.

Experimental Machine Learning of Quantum States.

Learning phase transitions from dynamics

Deep Neural Network Detects Quantum Phase Transition

Experimental learning of quantum states

Manufacturing an Artificial Intelligence Revolution

Quantum parameter estimation with a neural network

Accelerated Gradient Descent Escapes Saddle Points Faster than Gradient Descent

Machine Learning Out-of-Equilibrium Phases of Matter.

Super-polynomial and exponential improvements for quantum-enhanced reinforcement learning

On the role of synaptic stochasticity in training low-precision neural networks

Scalable Neural Network Decoders for Higher Dimensional Quantum Codes

First-order Methods Almost Always Avoid Saddle Points

Simulating the Ising Model with a Deep Convolutional Generative Adversarial Network

High-dimensional dynamics of generalization error in neural networks

Quantum Hopfield neural network

RG-inspired machine learning for lattice field theory