Learning to Inflate
arXiv:1810.05159 · doi:10.1088/1475-7516/2019/02/044
Abstract
Motivated by machine learning, we introduce a novel method for randomly generating inflationary potentials. Namely, we treat the Taylor coefficients of the potential as weights in a single-layer neural network and use gradient ascent to maximize the number of e-folds of inflation. Inflationary potentials "learned" in this way develop a critical point, which is typically a local maximum but may also be an inflection point. We study the phenomenology of the models along the gradient ascent trajectory, finding substantial agreement with experiment for large-field local maximum models and small-field inflection point models. For two-field models of inflation, the potential eventually learns a genuine multi-field model in which the inflaton curves significantly during the course of its descent.
arXiv comment31 pages, 12 figures, references added v2
References in corpus (65)
- The String Landscape, Black Holes and Gravity as the Weakest Force
- What would we learn by detecting a gravitational wave signal in the cosmic microwave background anisotropy?
- Scalar Speed Limits and Cosmology: Acceleration from D-cceleration
- N-flation
- Assisted inflation
- On the Possibility of Large Axion Decay Constants
- Classification without labels: Learning from mixed samples in high energy physics
- Learning Particle Physics by Example: Location-Aware Generative Adversarial Networks for Physics Synthesis
- Deep learning in color: towards automated quark/gluon jet discrimination
- Jet-Images -- Deep Learning Edition
- Observational Consequences of a Landscape
- Searching for New Physics with Deep Autoencoders
- Anomaly Detection for Resonant New Physics with Machine Learning
- What does inflation really predict?
- Transplanckian axions !?
- Towards an Explicit Model of D-brane Inflation
- A generic anti-QCD jet tagger
- Constraining Effective Field Theories with Machine Learning
- Fitting the Gamma-Ray Spectrum from Dark Matter with DMFIT: GLAST and the Galactic Center Region
- Weak Gravity Strongly Constrains Large-Field Axion Inflation
- Pileup Mitigation with Machine Learning (PUMML)
- On the Possibility of Large Axion Moduli Spaces
- Machine Learning of Calabi-Yau Volumes
- JUNIPR: a Framework for Unsupervised Machine Learning in Particle Physics
- Machine Learning in the String Landscape
- Learning to Classify from Impure Samples with High-Dimensional Data
- Search for dark matter produced with an energetic jet or a hadronically decaying W or Z boson at sqrt(s) = 13 TeV
- Deep Learning and AdS/CFT
- Evolving neural networks with genetic algorithms to study the String Landscape
- Weakly Supervised Classification in High Energy Physics
- Machine Learning CICY Threefolds
- Accidental Inflation in String Theory
- A Statistical Approach to Multifield Inflation: Many-field Perturbations Beyond Slow Roll
- Novel Jet Observables from Machine Learning
- Non-Gaussianity in Two-Field Inflation
- Jet Charge and Machine Learning
- (Machine) Learning to Do More with Less
- Machine learning cosmological structure formation
- Search for beautiful tetraquarks in the invariant-mass spectrum
- Expansion of All Multitrace Tree Level EYM Amplitudes
- Machine Learning and Cosmological Simulations II: Hydrodynamical Simulations
- Machine Learning and Cosmological Simulations I: Semi-Analytical Models
- Measurement of the t t-bar production cross section using events with one lepton and at least one jet in pp collisions at sqrt(s) = 13 TeV
- Charting an Inflationary Landscape with Random Matrix Theory
- Exploring a string-like landscape
- On Gaussian Random Supergravity
- GANs for generating EFT models
- Systematics of Axion Inflation in Calabi-Yau Hypersurfaces
- Persistent Homology and Non-Gaussianity
- On holographic entanglement entropy of Horndeski black holes
- Manyfield Inflation in Random Potentials
- Inflation in random Gaussian landscapes
- Seven Lessons from Manyfield Inflation in Random Potentials
- Inflation in Multi-field Modified DBM Potentials
- Learning non-Higgsable gauge groups in 4D F-theory
- Axion decay constants away from the lamppost
- Artificial Neural Network in Cosmic Landscape
- Initial conditions for slow-roll inflation in a random Gaussian landscape
- Inflation with a graceful exit in a random landscape
- Search for low-scale gravity signatures in multi-jet final states with the ATLAS detector at TeV
- Random Functions via Dyson Brownian Motion: Progress and Problems
- Inflation on a Slippery Slope
- Inflation as an Information Bottleneck - A strategy for identifying universality classes and making robust predictions
- Testing Two-Field Inflation
- Machine Learning Cosmic Expansion History
Cited by in corpus (10)
- Branes with Brains: Exploring String Vacua with Deep Reinforcement Learning
- Conditions for (No) Eternal Inflation
- Machine learning Calabi-Yau metrics
- Statistical Predictions in String Theory and Deep Generative Models
- Machine learning cosmic inflation
- Cosmic Inflation and Genetic Algorithms
- Optimal Inflationary Potentials
- A Triumvirate of AI Driven Theoretical Discovery
- Canonical Scalar Field Inflation with a Woods-Saxon Potential
- Universes as Big Data