arXiv:2608. 02705v1 Announce Type: cross Abstract: Comparing stochastically trained models requires estimating both a performance difference and its uncertainty from repeated runs.
Summary generated by The Flow from the publisher's feed. The full article lives at arXiv AI.
arXiv:2606. 03938v1 Announce Type: cross Abstract: Multi-epoch training is becoming the standard now that compute is growing faster than the supply of high-quality text.
arXiv:2608. 01074v1 Announce Type: new Abstract: Tabular data is used extensively in many real-world use cases.
arXiv:2602. 05786v3 Announce Type: replace Abstract: Tree-boosting is a widely used machine learning technique for tabular data.
Large hyperparameter sweeps for deep neural networks spend substantial compute on configurations that are effectively doomed from the first few epochs. We study whether a single training run's own early telemetry - per-epoch loss, training accuracy, gradient signal-to-noise ratio, weight-norm growth, and an activation-saturation snapshot - together with its sampled hyperparameters, can predict that run's eventual outcome without reference to other runs.
arXiv:2606. 12117v1 Announce Type: cross Abstract: Benchmark scores often misrepresent a large language model's (LLM's) knowledge, because they rely, e.
arXiv:2608. 01023v1 Announce Type: new Abstract: We present Caliber, an output-perturbation defense against model extraction that formulates noise selection as a calibration problem: how much the defense degrades the supervision signal used to train a surrogate, and the provable per-input query cost of recovering the clean logits.