---
title: Dimensionality Reduction with Dynamics & ML
url: https://www.ml-quant.com/papers/repec/eee-matcom-v-218-y-2024-i-c-p-98-111/
site: ML-Quant (https://www.ml-quant.com)
updated: 2026-09-26
license: Summaries CC BY 4.0; links go to the original sources
index: https://www.ml-quant.com/llms.txt
identifier: RePEc:eee:matcom:v:218:y:2024:i:c:p:98-111
source_url: https://econpapers.repec.org/scripts/redir.pf?u=http%3A%2F%2Fwww.sciencedirect.com%2Fscience%2Farticle%2Fpii%2FS0378475423004883%3Bh%3Drepec%3Aeee%3Amatcom%3Av%3A218%3Ay%3A2024%3Ai%3Ac%3Ap%3A98-111
featured: 2024-02-07
citations: unknown
topic: ML & AI Methods
---


# Dimensionality Reduction with Dynamics & ML

A new method that merges dynamical mechanisms and machine learning has been developed to simplify high-dimensional complex systems, demonstrating strong predictive capabilities even with noisy data.

- Source: https://econpapers.repec.org/scripts/redir.pf?u=http%3A%2F%2Fwww.sciencedirect.com%2Fscience%2Farticle%2Fpii%2FS0378475423004883%3Bh%3Drepec%3Aeee%3Amatcom%3Av%3A218%3Ay%3A2024%3Ai%3Ac%3Ap%3A98-111
- Identifier: RePEc:eee:matcom:v:218:y:2024:i:c:p:98-111
- Released: 2024-02-07
- First featured: Quant Letter No. 36 (2024-02-07): https://www.ml-quant.com/issues/2024-02-07/
- Citations (Semantic Scholar): not tracked
- Published in: not yet
- Topic: ML & AI Methods

## Related

- [Reconstruction vs. Generation: Taming Optimization Dilemma in Latent Diffusion Models](https://www.ml-quant.com/papers/arxiv/2501.01423/): The paper proposes a new model, VA-VAE, that aligns the latent space with pre-trained vision foundation models, enabling faster convergence of Diffusion Transformers in high-dimensional latent spaces and achieving top performance on ImageNet 256x256 generation.
- [Provably Efficient High-Dimensional Bandit Learning with Batched Feedbacks](https://www.ml-quant.com/papers/arxiv/2311.13180/): The study presents a sample-efficient algorithm for high-dimensional multi-armed contextual bandits with batched feedback, achieving regret bounds similar to those in fully sequential settings with fewer batches.
- [A backward differential deep learning-based algorithm for solving high-dimensional nonlinear backward stochastic differential equations](https://www.ml-quant.com/papers/arxiv/2404.08456/): The study introduces a new deep learning algorithm for solving complex backward stochastic differential equations, proving its effectiveness with numerous numerical tests.
- [Contrastive Moments: Unsupervised Halfspace Learning in Polynomial Time](https://www.ml-quant.com/papers/arxiv/2311.01435/): UHL: A new algorithm is introduced that can learn high-dimensional halfspaces in d-dimensional space in polynomial time, without needing labels.
- [Deep Penalty Methods: A Class of Deep Learning Algorithms for Solving High Dimensional Optimal Stopping Problems](https://www.ml-quant.com/papers/arxiv/2405.11392/): A proposed deep learning algorithm for optimal stopping problems shows accuracy and efficiency in American option pricing, with its error bound by the loss function and other parameters.
- [Deep multi-step mixed algorithm for high dimensional non-linear PDEs and associated BSDEs](https://www.ml-quant.com/papers/arxiv/2308.14487/): A new deep learning algorithm has been developed to solve complex mathematical equations, offering improved accuracy and less complexity than similar models.