Large language models for forecasting and anomaly detection: A systematic literature review

J Su, C Jiang, X **, Y Qiao, T **ao, H Ma… - arxiv preprint arxiv …, 2024‏ - arxiv.org
This systematic literature review comprehensively examines the application of Large
Language Models (LLMs) in forecasting and anomaly detection, highlighting the current …

Does learning require memorization? a short tale about a long tail

V Feldman - Proceedings of the 52nd Annual ACM SIGACT …, 2020‏ - dl.acm.org
State-of-the-art results on image recognition tasks are achieved using over-parameterized
learning algorithms that (nearly) perfectly fit the training set and are known to fit well even …

Formal limitations on the measurement of mutual information

D McAllester, K Stratos - International Conference on …, 2020‏ - proceedings.mlr.press
Measuring mutual information from finite data is difficult. Recent work has considered
variational methods maximizing a lower bound. In this paper, we prove that serious …

Optimal prediction of the number of unseen species

A Orlitsky, AT Suresh, Y Wu - Proceedings of the National Academy of …, 2016‏ - pnas.org
Estimating the number of unseen species is an important problem in many scientific
endeavors. Its most popular formulation, introduced by Fisher et al.[Fisher RA, Corbet AS …

Mauve scores for generative models: Theory and practice

K Pillutla, L Liu, J Thickstun, S Welleck… - Journal of Machine …, 2023‏ - jmlr.org
Generative artificial intelligence has made significant strides, producing text
indistinguishable from human prose and remarkably photorealistic images. Automatically …

Estimation of KL divergence: Optimal minimax rate

Y Bu, S Zou, Y Liang… - IEEE Transactions on …, 2018‏ - ieeexplore.ieee.org
The problem of estimating the Kullback-Leibler divergence D (P∥ Q) between two unknown
distributions P and Q is studied, under the assumption that the alphabet size k of the …

On universal features for high-dimensional learning and inference

SL Huang, A Makur, GW Wornell, L Zheng - arxiv preprint arxiv …, 2019‏ - arxiv.org
We consider the problem of identifying universal low-dimensional features from high-
dimensional data for inference tasks in settings involving learning. For such problems, we …

Instance-Optimal Private Density Estimation in the Wasserstein Distance

V Feldman, A McMillan… - Advances in Neural …, 2025‏ - proceedings.neurips.cc
Estimating the density of a distribution from samples is a fundamental problem in statistics. In
many practical settings, the Wasserstein distance is an appropriate error metric for density …

Instance optimal learning of discrete distributions

G Valiant, P Valiant - Proceedings of the forty-eighth annual ACM …, 2016‏ - dl.acm.org
We consider the following basic learning task: given independent draws from an unknown
distribution over a discrete support, output an approximation of the distribution that is as …

STADS: Software testing as species discovery

M Böhme - ACM Transactions on Software Engineering and …, 2018‏ - dl.acm.org
A fundamental challenge of software testing is the statistically well-grounded extrapolation
from program behaviors observed during testing. For instance, a security researcher who …