[图书][B] Introduction to high-dimensional statistics
C Giraud - 2021 - taylorfrancis.com
Praise for the first edition:"[This book] succeeds singularly at providing a structured
introduction to this active field of research.… it is arguably the most accessible overview yet …
introduction to this active field of research.… it is arguably the most accessible overview yet …
Soft truncation: A universal training technique of score-based diffusion model for high precision score estimation
Recent advances in diffusion models bring state-of-the-art performance on image
generation tasks. However, empirical results from previous research in diffusion models …
generation tasks. However, empirical results from previous research in diffusion models …
Towards theoretical understanding of inverse reinforcement learning
Inverse reinforcement learning (IRL) denotes a powerful family of algorithms for recovering a
reward function justifying the behavior demonstrated by an expert agent. A well-known …
reward function justifying the behavior demonstrated by an expert agent. A well-known …
On the optimality of the Hedge algorithm in the stochastic regime
J Mourtada, S Gaïffas - Journal of Machine Learning Research, 2019 - jmlr.org
In this paper, we study the behavior of the Hedge algorithm in the online stochastic setting.
We prove that anytime Hedge with decreasing learning rate, which is one of the simplest …
We prove that anytime Hedge with decreasing learning rate, which is one of the simplest …
[HTML][HTML] Examining the limits of predictability of human mobility
We challenge the upper bound of human-mobility predictability that is widely used to
corroborate the accuracy of mobility prediction models. We observe that extensions of …
corroborate the accuracy of mobility prediction models. We observe that extensions of …
Phase transitions and cyclic phenomena in bandits with switching constraints
D Simchi-Levi, Y Xu - Advances in Neural Information …, 2019 - proceedings.neurips.cc
We consider the classical stochastic multi-armed bandit problem with a constraint on the
total cost incurred by switching between actions. Under the unit switching cost structure …
total cost incurred by switching between actions. Under the unit switching cost structure …
Locally interacting diffusions as Markov random fields on path space
We consider a countable system of interacting (possibly non-Markovian) stochastic
differential equations driven by independent Brownian motions and indexed by the vertices …
differential equations driven by independent Brownian motions and indexed by the vertices …
Optimal subgroup selection
HWJ Reeve, TI Cannings, RJ Samworth - The Annals of Statistics, 2023 - projecteuclid.org
Optimal subgroup selection Page 1 The Annals of Statistics 2023, Vol. 51, No. 6, 2342–2365
https://doi.org/10.1214/23-AOS2328 © Institute of Mathematical Statistics, 2023 OPTIMAL …
https://doi.org/10.1214/23-AOS2328 © Institute of Mathematical Statistics, 2023 OPTIMAL …
Fast and accurate estimation of non-nested binomial hierarchical models using variational inference
M Goplerud - Bayesian Analysis, 2022 - projecteuclid.org
The supporting information contains derivations of the variational algorithm (Appendix A),
formal definitions and proofs of MAVB (Appendix B), results on accelerating CAVI using PX …
formal definitions and proofs of MAVB (Appendix B), results on accelerating CAVI using PX …
Bandit phase retrieval
T Lattimore, B Hao - Advances in Neural Information …, 2021 - proceedings.neurips.cc
We study a bandit version of phase retrieval where the learner chooses actions $(A_t) _ {t=
1}^ n $ in the $ d $-dimensional unit ball and the expected reward is $\langle …
1}^ n $ in the $ d $-dimensional unit ball and the expected reward is $\langle …