Research ideas

Every idea extracted from recent arXiv mathematics papers — verified and unverified. Click an idea to open its full card; badges show the empirical verdict.

2 ideas found

Status: Failed on benchmark Solves: Speed ML: Optimizer Clear all

✗ Failed on benchmark 2026

Poisson-Calibrated Candidate-Pool Scheduler

Replace a fixed number of randomly sampled continuous actions with a state-dependent candidate pool whose size is chosen from the predicted extreme-value error of the best candidate. If the local action deficit has order \(\|u-u^\star\|^\kappa\) in an effective dimension \(d\), the best sampled action has expected Bellman error proportional to \(N^{-\kappa/d}\). This gives an explicit stopping rule for increasing the pool only when the estimated residual action error is larger than the…

Useful8/10

Difficulty5/10

Novelty7/10

Dynamics Sample efficiency Speed Accuracy

Paper: Poisson Tangent Limits and Critical Policy Switching for Sampled Bellman Operators arXiv:2608.11549

✗ Failed on benchmark 2026

Bidirectional Saturation-Aware Trust Region

Replace a fixed gradient-clipping threshold or fixed optimizer trust region by a dynamic envelope that expands when proposed parameter updates are repeatedly clipped, contracts after clipping disappears, and tightens further during sustained unsaturated convergence. This transfers the paper's bidirectional modification mechanism to training while retaining an explicit safety cap on the actual parameter update.

Useful7/10

Difficulty4/10

Novelty6/10

Dynamics Stability Speed Accuracy

Paper: Low-Complexity Control Under Input Saturation and Performance Constraints: A Bidirectional Modification Scheme arXiv:2609.00827