Non-convex optimization for machine learning

P Jain, P Kar - Foundations and Trends® in Machine …, 2017 - nowpublishers.com
A vast majority of machine learning algorithms train their models and perform inference by
solving optimization problems. In order to capture the learning and prediction problems …

Identifying patterns in financial markets: Extending the statistical jump model for regime identification

AO Aydınhan, PN Kolm, JM Mulvey, Y Shu - Annals of Operations …, 2024 - Springer
Regime-driven models are popular for addressing temporal patterns in both financial market
performance and underlying stylized factors, wherein a regime describes periods with …

Sharp global convergence guarantees for iterative nonconvex optimization with random data

KA Chandrasekher, A Pananjady… - The Annals of …, 2023 - projecteuclid.org
Sharp global convergence guarantees for iterative nonconvex optimization with random data
Page 1 The Annals of Statistics 2023, Vol. 51, No. 1, 179–210 https://doi.org/10.1214/22-AOS2246 …

Driving style recognition method using braking characteristics based on hidden Markov model

C Deng, C Wu, N Lyu, Z Huang - PloS one, 2017 - journals.plos.org
Since the advantage of hidden Markov model in dealing with time series data and for the
sake of identifying driving style, three driving style (aggressive, moderate and mild) are …

Sublinear regret for learning pomdps

Y Xiong, N Chen, X Gao… - Production and …, 2022 - journals.sagepub.com
We study the model‐based undiscounted reinforcement learning for partially observable
Markov decision processes (POMDPs). The oracle we consider is the optimal policy of the …

HyperHMM: efficient inference of evolutionary and progressive dynamics on hypercubic transition graphs

MT Moen, IG Johnston - Bioinformatics, 2023 - academic.oup.com
Motivation The evolution of bacterial drug resistance and other features in biology, the
progression of cancer and other diseases and a wide range of broader questions can often …

Regime switching bandits

X Zhou, Y Xiong, N Chen… - Advances in Neural …, 2021 - proceedings.neurips.cc
We study a multi-armed bandit problem where the rewards exhibit regime switching.
Specifically, the distributions of the random rewards generated from all arms are modulated …

Model agnostic time series analysis via matrix estimation

A Agarwal, MJ Amjad, D Shah, D Shen - Proceedings of the ACM on …, 2018 - dl.acm.org
We propose an algorithm to impute and forecast a time series by transforming the observed
time series into a matrix, utilizing matrix estimation to recover missing values and de-noise …

A hidden markov model for seismocardiography

J Wahlström, I Skog, P Händel… - IEEE Transactions …, 2017 - ieeexplore.ieee.org
We propose a hidden Markov model approach for processing seismocardiograms. The
seismocardiogram morphology is learned using the expectation-maximization algorithm …

Sharp global convergence guarantees for iterative nonconvex optimization: A Gaussian process perspective

KA Chandrasekher, A Pananjady… - arXiv preprint arXiv …, 2021 - arxiv.org
We consider a general class of regression models with normally distributed covariates, and
the associated nonconvex problem of fitting these models from data. We develop a general …