arXiv Machine Learning
Selective Prediction Intervals: Jointly Learning to Predict, Bound, and Abstain
Read the original on arXiv Machine Learning →The Flow has not summarised this story yet — read it at arXiv Machine Learning.
Related stories
arXiv AI
Oct 12
Revisiting Tabular Deep Regression: Objectives and the Limits of Global Early Stopping
The paper systematically evaluates regression objectives for tabular deep learning across many datasets and neural backbones, finding that most alternatives to Mean Squared Error (MSE) offer limited or inconsistent gains, while quantile loss consistently improves performance. It identifies a limitation of global early stopping: different noise levels in target regions reach optimal performance at different epochs, causing a compromise. To address this, the authors propose a heteroskedasticity‑aware extension of quantile loss using input‑dependent label smoothing, which outperforms standard quantile loss on several backbones.
arXiv Machine Learning
Aug 21
$TCP_\alpha$: Margin-Controlled Confidence estimation for reliable Music Information Retrieval
arXiv:2608. 20326v1 Announce Type: cross Abstract: Deep neural networks are often overconfident, assigning high confidence even to incorrect predictions.
Hugging Face Trending Papers
Aug 20
$TCP_α$: Margin-Controlled Confidence estimation for reliable Music Information Retrieval
Deep neural networks are often overconfident, assigning high confidence even to incorrect predictions. Consequently, users lack a reliable signal for deciding when a prediction can be trusted.
arXiv AI
Oct 15
Certify the Decision, Not Every Score: Exact Top-k Selection from Few Evaluations
arXiv:2610.14996v1 Announce Type: new Abstract: Choosing a few robust algorithms or schedules can require evaluating every candidate under many adverse scenarios, even though an agent only needs to i...
arXiv AI
Jul 28
DeepLook: Deeper Thinking with Lookahead
arXiv:2607. 22602v1 Announce Type: new Abstract: Inference-time scaling has emerged as a powerful paradigm for improving large language model reasoning, often delivering larger gains on difficult reasoning tasks than parameter scaling alone.
arXiv Machine Learning
Jul 8
Heckman-Corrected Epistemic Uncertainty: Selection on Unobservables Defeats Importance Weighting
arXiv:2607. 05806v1 Announce Type: new Abstract: Training data for machine learning is routinely collected by a selection process the model never sees: loans are observed only when granted, outcomes only when a test was ordered.