Research map / Time series / Causal and generative time series
Adaptive Quantization in Generative Flow Networks for Probabilistic Sequential Prediction
Nadhir Hassen, Zhen Zhang, Johan W. Verjans
Read the paperCheck your idea against 137,217 papers
AI-extracted summary. Written by AI from the paper's abstract only. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Proposes Temporal GFNs, adapting Generative Flow Networks with adaptive quantization to produce calibrated probabilistic forecasts over continuous future values.
Problem
Probabilistic time series forecasting requires capturing uncertainty and temporal dependencies, and generating calibrated distributions over continuous future values remains challenging.
Approach
Adapts Generative Flow Networks to sequential prediction, using adaptive quantization of continuous values so the flow model can generate calibrated probability distributions over future time series values.
Experimental setup
Builds on: Generative Flow Networks
Closest papers by meaning
- Pre-Training and Fine-Tuning Generative Flow Networks (ICLR 2024 · similarity 0.88)
- Flow Factorization for Efficient Generative Flow Networks (AAAI 2025 · similarity 0.88)
- Looking Backward: Retrospective Backward Synthesis for Goal-Conditioned GFlowNets (ICLR 2025 · similarity 0.88)
- Flow Matching with Gaussian Process Priors for Probabilistic Time Series Forecasting (ICLR 2025 · similarity 0.88)
- Pessimistic Backward Policy for GFlowNets (NeurIPS 2024 · similarity 0.88)
- Optimizing Backward Policies in GFlowNets via Trajectory Likelihood Maximization (ICLR 2025 · similarity 0.87)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
