The study introduces RegimeShift‑Surrogates, a streaming benchmark that tests surrogate models across eight tasks and multiple regimes. It compares revalidation—choosing the model with lowest current‑window validation loss—to stateful adaptive controllers and finds that revalidation consistently outperforms stateful methods, achieving lower mean log regret in most task‑scenario combinations. The results suggest that fresh validation evidence is more valuable than carrying over past evidence when dealing with distribution shifts.
arXiv:2608. 01130v1 Announce Type: new Abstract: A broad range of models face the mismatch where they are updated through trajectory losses but are evaluated by downstream task reward.
arXiv:2607. 23667v1 Announce Type: cross Abstract: A flow surrogate validated on a simple regime is often taken as evidence that the approach will carry to a richer one.
arXiv:2608. 02636v1 Announce Type: cross Abstract: Self-evolving skill systems promise to improve agents by turning execution feedback into persistent skill updates without changing the underlying model.
The paper introduces Online Surrogate Repair (OSR), a closed‑loop algorithm that decouples the frequency of high‑fidelity evaluations from the length of an agent’s search by selectively updating a surrogate model with sparse, high‑fidelity data. An acquisition rule determines which candidate designs receive expensive evaluations, and the resulting labels refine the surrogate for subsequent episodes. Experiments on synthetic environments and the MADE benchmark show that OSR can reduce regret more efficiently than fixed‑surrogate approaches, requiring fewer oracle queries than high‑fidelity feedback after every episode.
arXiv:2603. 28921v3 Announce Type: replace-cross Abstract: The critical damping condition of the damped harmonic oscillator model of SGD with momentum (Qian, 1999) yields a momentum schedule with no tuned hyperparameters: mu(t) = 1 - 2*sqrt(alpha(t)).
arXiv:2609. 20193v1 Announce Type: new Abstract: Retrieval plug-ins supply a deep forecaster with information its lookback window cannot carry.
arXiv:2608.20998v1 Announce Type: new Abstract: Reservoir computing (RC) couples a fixed recurrent dynamical system with a trained lightweight readout, but this efficiency is partly lost during hyper...
The paper introduces a sparse, residual world model that focuses on predicting only the changes in a scene by using a per-object change gate and a residual delta head. On a MuJoCo tabletop pushing benchmark, this approach outperforms a dense multilayer perceptron, achieving 2.5 to 4.6 times better next‑state pose accuracy with 8.6 to 11.1 times fewer parameters, maintaining high change‑detection F1 scores, and showing strong transfer across object counts. In autoregressive rollout and sampling‑based planning, the sparse model accumulates less error and enables successful planning where dense models fail.
The paper introduces OrbitTrace, a benchmark of 50 physics‑grounded compute‑availability traces from satellite orbits, and investigates whether specialized interruption‑resilient optimizers are needed when training is interrupted by predictable compute gaps. Experiments on CIFAR‑10/ResNet‑18 and GPT‑2/AdamW show that a strong checkpoint‑and‑resume baseline that preserves full optimizer state and indexes learning‑rate schedules in effective time matches uninterrupted training, rendering most availability‑aware methods unnecessary. Only in a narrow regime—large models with non‑persistable optimizer state and frequent short pauses—does reactive adaptation recover a modest portion of the state‑loss penalty, and even this benefit disappears for eclipse‑scale gaps.
arXiv:2609.23686v1 Announce Type: new Abstract: Patch-based autoregressive time-series forecasting often ties input representation, learned transitions, and recursive execution to one patch length. W...
arXiv:2607. 16268v1 Announce Type: new Abstract: Adaptive optimizers such as Adam and AdamW apply the same update rule regardless of whether training is in a chaotic early phase or near convergence.
arXiv:2608. 19488v1 Announce Type: new Abstract: Production machine learning systems degrade under concept drift, yet practitioners have little principled guidance on when to retrain.