Show newer

Algorithmic Stability of Heavy-Tailed Stochastic Gradient Descent on Least Squares. (arXiv:2206.01274v1 [stat.ML]) arxiv.org/abs/2206.01274

Lottery Tickets on a Data Diet: Finding Initializations with Sparse Trainable Networks. (arXiv:2206.01278v1 [cs.LG]) arxiv.org/abs/2206.01278

Sequential Permutation Testing of Random Forest Variable Importance Measures. (arXiv:2206.01284v1 [stat.ME]) arxiv.org/abs/2206.01284

Rashomon Capacity: A Metric for Predictive Multiplicity in Probabilistic Classification. (arXiv:2206.01295v1 [cs.LG]) arxiv.org/abs/2206.01295

Likelihood-based Instrumental Variable Methods for Cox Proportional Hazard Models. (arXiv:2206.01302v1 [stat.ME]) arxiv.org/abs/2206.01302

Sample-Efficient Reinforcement Learning of Partially Observable Markov Games. (arXiv:2206.01315v1 [cs.LG]) arxiv.org/abs/2206.01315

Optimal Activation Functions for the Random Features Regression Model. (arXiv:2206.01332v1 [stat.ML]) arxiv.org/abs/2206.01332

Split-kl and PAC-Bayes-split-kl Inequalities. (arXiv:2206.00706v1 [stat.ML]) arxiv.org/abs/2206.00706

Collaborative Learning of Distributions under Heterogeneity and Communication Constraints. (arXiv:2206.00707v1 [stat.ML]) arxiv.org/abs/2206.00707

Data Augmentation MCMC for Bayesian Inference from Privatized Data. (arXiv:2206.00710v1 [stat.ME]) arxiv.org/abs/2206.00710

Bayesian Inference for the Multinomial Probit Model under Gaussian Prior Distribution. (arXiv:2206.00720v1 [stat.ME]) arxiv.org/abs/2206.00720

Modified Galton-Watson processes with immigration under an alternative offspring mechanism. (arXiv:2206.00736v1 [stat.ME]) arxiv.org/abs/2206.00736

Nest Your Adaptive Algorithm for Parameter-Agnostic Nonconvex Minimax Optimization. (arXiv:2206.00743v1 [math.OC]) arxiv.org/abs/2206.00743

A Log-Linear Time Sequential Optimal Calibration Algorithm for Quantized Isotonic L2 Regression. (arXiv:2206.00744v1 [cs.LG]) arxiv.org/abs/2206.00744

Bayesian sample size determination for causal discovery. (arXiv:2206.00755v1 [stat.ME]) arxiv.org/abs/2206.00755

On Reinforcement Learning and Distribution Matching for Fine-Tuning Language Models with no Catastrophic Forgetting. (arXiv:2206.00761v1 [cs.LG]) arxiv.org/abs/2206.00761

Confidence Intervals for Recursive Journal Impact Factors. (arXiv:2206.00004v1 [econ.GN]) arxiv.org/abs/2206.00004

Order statistics from exchangeable random variables are always sufficient. (arXiv:2206.00044v1 [math.ST]) arxiv.org/abs/2206.00044

Show older
Qoto Mastodon

QOTO: Question Others to Teach Ourselves
An inclusive, Academic Freedom, instance
All cultures welcome.
Hate speech and harassment strictly forbidden.