Generating Financial Time Series by Matching Random Convolutional Features
cs.LG, q-fin.ST
Submitted: 2026-06-03
Updated: 2026-11-02
Code: https://github.com/binance/binance-public-data
Terminology
Sources
- A Data-driven Market Simulator for Small Data Environments
- Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling
- Applications of Signature Methods to Market Anomaly Detection
- Randomized Signature Methods in Optimal Portfolio Selection
- Universal randomised signatures for generative time series modelling
- Free probability, path developments and signature kernels as universal scaling limits
- Real-valued (Medical) Time Series Generation with Recurrent Conditional GANs
- Distributional Adversarial Attacks and Training in Deep Hedging
- Training Generative Adversarial Networks with Limited Data
- Restricted Path Characteristic Function Determines the Law of Stochastic Processes
- G-Signatures: Global Graph Propagation With Randomized Signatures
Related papers
- A Physics-Regulated Neural Framework for Learning 3D Grain Growth Dynamics
- FlexMoE: Learning One-for-All Multi-Budget Expert Pruning for Flexible MoE Deployment
- OptiMind: Improving Small Language Models for Optimization Modeling through Formulation Guidance and Multi-Turn Learning
- Staying in the Sweet Spot: Boost Reasoning Evolution via Responsive Rollout Difficulty Manipulation
- Examining the Impact of Data and Training Methods on Emergent and Subliminal Misalignment
- Rethinking Black-Box On-Policy Distillation: A Rubric-based Analysis