Concentration inequalities for statistical inference

H Zhang, SX Chen - arxiv preprint arxiv:2011.02258, 2020‏ - arxiv.org
This paper gives a review of concentration inequalities which are widely employed in non-
asymptotical analyses of mathematical statistics in a wide range of settings, from distribution …

Clique topology reveals intrinsic geometric structure in neural correlations

C Giusti, E Pastalkova, C Curto… - Proceedings of the …, 2015‏ - National Acad Sciences
Detecting meaningful structure in neural activity and connectivity data is challenging in the
presence of hidden nonlinearities, where traditional eigenvalue-based methods may be …

Statistical inference in a directed network model with covariates

T Yan, B Jiang, SE Fienberg, C Leng - Journal of the American …, 2019‏ - Taylor & Francis
Networks are often characterized by node heterogeneity for which nodes exhibit different
degrees of interaction and link homophily for which nodes sharing common features tend to …

Inference using noisy degrees: Differentially private -model and synthetic graphs

V Karwa, A Slavković - 2016‏ - projecteuclid.org
Inference using noisy degrees: Differentially private beta-model and synthetic graphs Page 1
The Annals of Statistics 2016, Vol. 44, No. 1, 87–112 DOI: 10.1214/15-AOS1358 © Institute of …

Asymptotics in directed exponential random graph models with an increasing bi-degree sequence

T Yan, C Leng, J Zhu - 2016‏ - projecteuclid.org
Supplement to “Asymptotics in directed exponential random graph models with an
increasing bi-degree sequence.”. The supplemental material contains proofs for the lemmas …

Distributed differential privacy in multi-armed bandits

SR Chowdhury, X Zhou - arxiv preprint arxiv:2206.05772, 2022‏ - arxiv.org
We consider the standard $ K $-armed bandit problem under a distributed trust model of
differential privacy (DP), which enables to guarantee privacy without a trustworthy server …

Modeling attrition in recommender systems with departing bandits

O Ben-Porat, L Cohen, L Leqi, ZC Lipton… - Proceedings of the AAAI …, 2022‏ - ojs.aaai.org
Traditionally, when recommender systems are formalized as multi-armed bandits, the policy
of the recommender system influences the rewards accrued, but not the length of interaction …

Asymptotics in undirected random graph models parameterized by the strengths of vertices

T Yan, H Qin, H Wang - Statistica Sinica, 2016‏ - JSTOR
To capture the heterozygosity of vertex degrees of networks and understand their
distributions, a class of random graph models parameterized by the strengths of vertices is …

Detection thresholds for the -model on sparse graphs

R Mukherjee, S Mukherjee, S Sen - 2018‏ - projecteuclid.org
Detection thresholds for the beta-model on sparse graphs Page 1 The Annals of Statistics
2018, Vol. 46, No. 3, 1288–1317 https://doi.org/10.1214/17-AOS1585 © Institute of …

Hidden hypergraphs, error-correcting codes, and critical learning in hopfield networks

C Hillar, T Chan, R Taubman, D Rolnick - Entropy, 2021‏ - mdpi.com
In 1943, McCulloch and Pitts introduced a discrete recurrent neural network as a model for
computation in brains. The work inspired breakthroughs such as the first computer design …