The paper introduces a statistical framework for post‑training hyperparameter selection, emphasizing the learn‑then‑test (LTT) paradigm. It treats hyperparameter tuning as a multiple hypothesis testing problem over a candidate set, enabling the selection of hyperparameters that meet specified reliability constraints such as risk bounds or information‑theoretic limits. The framework provides finite‑sample control of error probabilities using p‑values, e‑values, and concentration inequalities derived from first principles.
arXiv:2606. 25601v1 Announce Type: cross Abstract: Hyperparameter selection is a critical step in the deployment of modern artificial intelligence systems, given the need to tune degrees of freedom such as inference-time parameters, implementation-level settings, and thresholds driving decision rules.
arXiv:2604. 13130v2 Announce Type: replace Abstract: We study learning to learn through the lens of hyperparameter tuning.
arXiv:2610.27895v1 Announce Type: cross Abstract: Direct preference optimisation (DPO) is widely used for language model post-training, but its performance depends strongly on the choice of its hyper...
HyperMC is a multi‑fidelity hyperparameter tuning framework for stochastic gradient Markov chain Monte Carlo (SGMCMC) that combines Hyperband-style resource allocation with kernel Stein discrepancy (KSD) evaluation. It uses successive‑halving brackets to explore a continuous hyperparameter space while progressively refining promising configurations within a fixed computational budget. Robust HyperMC further introduces global grid initialization and elite‑guided local refinement to reduce sensitivity to random candidate generation and noisy evaluations, and theoretical analysis shows that the successive‑halving component selects a near‑optimal configuration with high probability under suitable conditions.
arXiv:2211. 14411v5 Announce Type: replace-cross Abstract: Hyperparameter optimization (HPO) is crucial for strong performance of deep learning algorithms and real-world applications often impose some constraints, such as on memory usage or latency, on top of the performance requirement.
arXiv:2606. 15569v1 Announce Type: new Abstract: Test-time training (TTT) adapts a pretrained model to each prompt via parameter updates, improving accuracy under pretraining-to-test distribution shifts.
arXiv:2405. 04376v4 Announce Type: replace Abstract: Hyperparameter tuning, particularly the selection of an appropriate learning rate in adaptive gradient training methods, remains a challenge.
arXiv:2602. 05786v3 Announce Type: replace Abstract: Tree-boosting is a widely used machine learning technique for tabular data.
arXiv:2608. 13793v1 Announce Type: cross Abstract: Machine learning (ML) has become an indispensable part of modern engineering design workflows.
ExpTest is an autonomous learning‑rate controller that uses the training loss curve as an online signal to perform sequential statistical tests on theoretically motivated windows, detecting convergent behavior and triggering learning‑rate reductions. It combines a covariance‑based initial learning‑rate estimate, curvature‑motivated window sizing, and a two‑phase test‑driven decay, relying on the approximately exponential decay predicted under linearized network dynamics. Experiments on regression, classification, forecasting, and natural‑language tasks across various architectures show that ExpTest achieves competitive performance compared to hand‑tuned SGD baselines and recent learning‑rate‑free methods, without requiring manual initial learning‑rate selection or predefined scheduling.
The paper investigates the limits of optimal data selection for machine learning, showing that minimizing population error is impossible without a validation set much larger than the training set. It introduces a new concept called faithfulness, providing an estimable upper bound on the performance gap between training on a subset and on the full dataset. The authors propose a swap‑based local search algorithm that iteratively reduces this bound and demonstrate its effectiveness on CIFAR‑10 and CIFAR‑100 datasets.
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...