MétaCan
Menu
Back to cohort
Record W7132873076

Efficient Deep Learning Methods for Solving High-dimensional Partial Differential Equations for Applications in Option Pricing

2022· dissertation· W7132873076 on OpenAlexaff
Raj Gaurangbhai Patel

Bibliographic record

VenueTSpace · 2022
Typedissertation
Language
FieldPhysics and Astronomy
TopicModel Reduction and Neural Networks
Canadian institutionsUniversity of Toronto
Fundersnot available
KeywordsCurse of dimensionalityBenchmark (surveying)Artificial neural networkDeep learningReinforcement learningConvergence (economics)Variety (cybernetics)Partial differential equation
DOInot available

Abstract

fetched live from OpenAlex

Partial Differential Equations (PDEs) are used to model a variety of dynamical systems around us. Recent advances in deep learning have enabled us to solve these PDEs in higher dimensions by addressing the Curse of Dimensionality (COD). However, these approaches are constrained by training time and memory. To tackle these shortcomings, we introduce three approaches starting with Multi-Level Dense Neural Networks (ML-DNN). ML-DNN draws inspiration from Multi-Level Monte-Carlo to efficiently sample and perform hierarchical learning thereby providing substantial time savings compared to the classical Dense Neural Network (DNN). Next, we implement Tensor Neural Networks, a quantum-inspired architecture that provides significant parameter savings and faster convergence while attaining the same accuracy as compared to a DNN. Finally, we introduce a model-based Reinforcement Learning algorithm which addresses the COD and is independent of the PDE family. We benchmark these models on parabolic PDEs, empirically showing their advantages over the current state-of-the-art models.

Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.

How this classification was reachedexpand

Full frame machine prediction

Teacher imitation

Not calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.

metaresearch head score (Codex)0.001
metaresearch head score (Gemma)0.003
Version: metacan-v3-hybrid-931329e0061cValidation status: machine_predicted_unvalidated
Candidate categoriesnone
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Simulation or modeling · Consensus signal: Simulation or modeling
GenreCandidate signal: Empirical · Consensus signal: none
Teacher disagreement score0.006
Threshold uncertainty score0.011

Distilled classifier scores by category (both heads)

CategoryCodexGemma
Metaresearch0.0010.003
Meta-epidemiology (narrow)0.0010.000
Meta-epidemiology (broad)0.0010.001
Bibliometrics0.0000.001
Science and technology studies0.0000.001
Scholarly communication0.0010.001
Open science0.0010.001
Research integrity0.0010.003
Insufficient payload (model declined to judge)0.0030.001

Machine scores (provisional)

The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.

Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.

Opus teacher head0.029
GPT teacher head0.389
Teacher spread0.360 · how far apart the two teachers sit on this one work
Validation statusscore_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from it

Classification

machine, unvalidated

Machine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.

The models applied no category: nothing in the taxonomy fit this work.
Study designSimulation or modeling
Domainnot available
GenreEmpirical

How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".

Quick stats

Citations0
Published2022
Admission routes1
Has abstractyes

Explore more

Same venueTSpaceSame topicModel Reduction and Neural NetworksFrench-language works237,207