Truncated backpropagation through time induces a two-sided gradient turnpike property
eess.SY, cs.LG, cs.SY, math.OC
Submitted: 2026-11-05
Updated: 2026-11-05
Code: https://github.com/alesco-research/tbptt-gradient-turnpikes
Sources
- A Critical Review of Recurrent Neural Networks for Sequence Learning
- Learning neural state-space models: do we need a state estimator?
- Unbiasing Truncated Backpropagation Through Time
- Performance guarantees for optimization-based state estimation using turnpike properties
- Mamba: Linear-Time Sequence Modeling with Selective State Spaces
Related papers
- Industrial Load Modeling and Optimization for Market-Based Interaction with Power Systems
- Exact and Approximate Convex Reformulation of Linear Stochastic Optimal Control with Chance Constraints
- Certified Set Convergence for Piecewise Affine Systems
- Symbolic Control for Stochastic Systems via Finite Parity Games
- Multiobjective optimization-based design and dispatch of islanded, hybrid microgrids for remote, off-grid communities in sub-Saharan Africa
- Physiology-informed layered sensing for intelligent human-exoskeleton interaction