HERO: History-Enriched Rollout Training for Long-Horizon Autoregressive Neural Operators

• URL: http://arxiv.org/abs/2607.29135v1
• Date: Fri, 31 Jul 2026 08:05:46 GMT
• Title: HERO: History-Enriched Rollout Training for Long-Horizon Autoregressive Neural Operators
• Abstract summary: Autoregressive rollout feeds every prediction error back as input, so local errors accumulate.<n>Existing rollout-training strategies reduce the mismatch between training inputs and self-generated states, yet their supervision still measures only the absolute discrepancy from the ground-truth trajectory.<n>We propose history-enriched rollout training (HERO), which augments conventional absolute trajectory supervision with relative supervision derived from the model's optimization history.
• Score: 17.3214708475049
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Neural operators provide fast surrogates for time-dependent partial differential equations (PDEs) by applying a learned evolution operator recursively to its own predictions, but this autoregressive rollout feeds every prediction error back as input, so local errors accumulate. Existing rollout-training strategies reduce the mismatch between training inputs and self-generated states, yet their supervision still measures only the absolute discrepancy from the ground-truth trajectory. Such supervision is therefore uninformative about whether the operator has overcome the long-horizon failure behaviors it exhibited earlier during optimization. We propose history-enriched rollout training (HERO), which augments conventional absolute trajectory supervision with relative supervision derived from the model's optimization history. HERO ranks detached candidate rollouts from a periodically refreshed lagged operator, the current model, and a perturbed input by rollout error, spectral discrepancy, energy drift, and error growth, and selects the strongest failure trajectory as reference. This reference enters a margin-based objective as a fixed comparison baseline, inducing a bounded, sample-dependent reweighting of the ground-truth rollout gradient rather than an independent gradient direction, which we further analyze theoretically. Experiments on nine PDE benchmarks with spectral and attention-based backbones show that HERO consistently improves long-horizon accuracy, stable rollout length, and out-of-distribution robustness at no inference-time cost. These results indicate that history-enriched relative supervision is effective for stabilizing long-horizon autoregressive prediction.

Related papers

• FlowBalance: Verifier-Grounded Self-Improvement from On-Policy Reasoning Experience [18.64380706071327]
  FlowBalance is a verifier-grounded self-improvement method that learns a normalized distribution over complete responses.<n>For each on-policy trajectory, a frozen training-time view of the same policy uses privileged context to produce token-level log-probability gains.<n>Our analysis establishes within-group contrast preservation, a minimum-change reverse-KL characterization, monotonic verifier control of target reward, and an exact correction against false-positive self-guidance on rejected responses.
  arXiv  Detail & Related papers  (2026-09-03T00:47:11Z)
• LC-GRPO: Bridging Train-Inference Gap for Flow-Based GRPO with Langevin Correction [59.32834240526981]
  Flow-based generative models are typically sampled by solving a deterministic ordinary differential equation (ODE)<n>Existing GRPO methods for flow models replace the Euler-time ODE with aotropic differential equation (SDE) during training.<n>We introduce LC-GRPO, a flow-based GRPO framework with Langevin correction targeting the marginal distribution at the resulting timestep.
  arXiv  Detail & Related papers  (2026-08-06T04:47:57Z)
• H$^2$SD: Hybrid Hindsight Self-Distillation [61.71131241473028]
  Reinforcement learning with verifiable rewards (RLVR) provides reliable outcome supervision for language model reasoning.<n>Existing self-distillation methods add a privileged teacher but typically assign it a fixed role.<n>We introduce Hybrid Hindsight Self-Distillation ($mathrmH2mathrmSD$), which jointly adapts teacher context and update strategy to trajectory correctness.
  arXiv  Detail & Related papers  (2026-07-21T10:47:27Z)
• Autoregression-Free Neural Operators for Time-Dependent PDEs [22.734418195465043]
  We propose Autoregression-Free Neural Operators (AFNO), which map the time evolution of PDEs into a latent space and model continuous-time vector fields within it.<n>We show that AFNO improves long-horizon prediction stability and consistently reduces rollout errors compared with the baselines.
  arXiv  Detail & Related papers  (2026-05-25T04:28:41Z)
• RAVEN: Real-time Autoregressive Video Extrapolation with Consistency-model GRPO [53.38929612273108]
  Causal autoregressive video diffusion models support real-time streaming generation by extrapolating future chunks from previously generated content.<n>We introduce the Real-time Autoregressive Video Extrapolation Network (RAVEN), a training-time test framework that repacks each self rollout into an interleaved sequence of clean historical endpoints.
  arXiv  Detail & Related papers  (2026-05-14T17:59:30Z)
• Mitigating Error Amplification in Fast Adversarial Training [58.74042726356826]
  Fast Adversarial Training (FAT) has proven effective in enhancing model robustness by encouraging networks to learn perturbation-invariant representations.<n>FAT often suffers from catastrophic overfitting (CO), where the model overfits to the training attack and fails to generalize to unseen ones.<n>We propose a Distribution-aware Dynamic Guidance (DDG) strategy that dynamically adjusts both the perturbation budget and supervision signal.
  arXiv  Detail & Related papers  (2026-04-27T11:23:18Z)
• Temporal Imbalance of Positive and Negative Supervision in Class-Incremental Learning [10.054396813990481]
  CIL faces the core challenge of catastrophic forgetting, often manifested as a prediction bias toward new classes.<n>Existing methods mainly attribute this bias to intra-task class imbalance and focus on corrections at the classifier head.<n>We propose Temporal-Adjusted Loss (TAL), which uses a temporal decay kernel to construct a supervision strength vector and dynamically reweight the negative supervision in cross-entropy loss.
  arXiv  Detail & Related papers  (2026-03-02T01:57:52Z)
• Adaptive recurrent flow map operator learning for reaction diffusion dynamics [0.9137554315375919]
  We develop an operator learner with adaptive recurrent training (DDOL-ART) using a robust recurrent strategy with lightweight validation milestones.<n>DDOL-ART learns one-step operators that remain stable under long rollouts and generalize zero-shot to strong shifts.<n>It is several-fold faster than a physics-based numerical-loss operator learner (NLOL) under matched settings.
  arXiv  Detail & Related papers  (2026-02-10T07:33:13Z)
• Training Instabilities Induce Flatness Bias in Gradient Descent [6.628332915214955]
  Modern deep networks often achieve their best performance beyond a stability threshold.<n>We show that training instabilities induce an implicit bias in GD, driving parameters toward flatter regions of the loss landscape.<n>We also show that restoring instabilities in Adam further improves generalization.
  arXiv  Detail & Related papers  (2025-11-16T11:26:25Z)
• ResAD: Normalized Residual Trajectory Modeling for End-to-End Autonomous Driving [64.42138266293202]
  ResAD is a Normalized Residual Trajectory Modeling framework.<n>It reframes the learning task to predict the residual deviation from an inertial reference.<n>On the NAVSIM benchmark, ResAD achieves a state-of-the-art PDMS of 88.6 using a vanilla diffusion policy.
  arXiv  Detail & Related papers  (2025-10-09T17:59:36Z)
• Understanding, Predicting and Better Resolving Q-Value Divergence in Offline-RL [86.0987896274354]
  We first identify a fundamental pattern, self-excitation, as the primary cause of Q-value estimation divergence in offline RL. We then propose a novel Self-Excite Eigenvalue Measure (SEEM) metric to measure the evolving property of Q-network at training. For the first time, our theory can reliably decide whether the training will diverge at an early stage.
  arXiv  Detail & Related papers  (2023-10-06T17:57:44Z)
• Provable Guarantees for Generative Behavior Cloning: Bridging Low-Level Stability and High-Level Behavior [51.60683890503293]
  We propose a theoretical framework for studying behavior cloning of complex expert demonstrations using generative modeling. We show that pure supervised cloning can generate trajectories matching the per-time step distribution of arbitrary expert trajectories.
  arXiv  Detail & Related papers  (2023-07-27T04:27:26Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.