Sohom Bhattacharya

Sohom Bhattacharya

Auto-generated profile, based on publicly available information

Sohom Bhattacharya

Department of Statistics University of Florida

Research Focus & Metrics

Academic Career Length

7Years (2020-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
25 April 2022 in IEEE Transactions on Information Theory
Verified
Journal Article
Closed access
SBSohom Bhattacharya
Sohom Bhattacharya
SCSourav Chatterjee
Sourav Chatterjee
The problem of completing a large matrix with lots of missing entries has received widespread attention in the last couple of decades. Two popular approaches to the matrix completion problem are based on singular value thresholding and nuclear norm minimization. Most of the past works on this subject assume that there is a single number $p$ such that each entry of the matrix is available independently with probability $p$ and missing otherwise. This assumption may not be realistic for many applications. In this work, we replace it with the assumption that the probability that an entry is available is an unknown function $f$ of the entry itself. For example, if the entry is the rating given to a movie by a viewer, then it seems plausible that high value entries have greater probability of being available than low value entries. We propose two new estimators, based on singular value thresholding and nuclear norm minimization, to recover the matrix under this assumption. The estimators involve no tuning parameters, and are shown to be consistent under a low rank assumption. We also provide a consistent estimator of the unknown function $f$ .

6 April 2021 in Random Structures & Algorithms
Verified
Journal Article
Closed access
PDF file
SBSohom Bhattacharya
Sohom Bhattacharya
ADAmir Dembo
Amir Dembo

3 March 2025 in IEEE Transactions on Information Theory
Verified
Journal Article
Closed access
SBSohom Bhattacharya
Sohom Bhattacharya
RMRajarshi Mukherjee
Rajarshi Mukherjee
GRGourab Ray
Gourab Ray
In this paper, we study a structured signal detection problem in Ferromagnetic Ising models with examples encompassing Ising Models on lattices, and Mean-Field type Ising Models such as dense Erdős-Rényi, and dense random regular graphs. We provide sharp constants of detection in each of these cases and thereby pinpoint an asymptotically precise relationship between the detection problem with the underlying dependence. To obtain this sharp characterization of the detection boundary at the level of sharp multiplicative constants, we derive necessary moderate deviation bounds for partial summands of magnetizations which might be of independent interest. Finally, we demonstrate how our tests can be designed to be adaptive over the strength of dependence present in the respective models.

18 May 2026 in Journal of the American Statistical Association
Verified
Journal Article
Closed access
SBSohom Bhattacharya
Sohom Bhattacharya
JFJianqing Fan
Jianqing Fan
JHJikai Hou
Jikai Hou
1 IntroductionIn various fields of study, such as citation networks, protein interactions, health, finance, trade, and social networks, we often come across large amounts of data that describe the ...

4 June 2025 in Biometrika
Verified
Journal Article
Closed access
SBSohom Bhattacharya
Sohom Bhattacharya
RMRajarshi Mukherjee
Rajarshi Mukherjee
EOElizabeth L Ogburn
Elizabeth L Ogburn
Summary: identified the issue of ′nonsense correlations’ in time series data, where dependence within each of two random vectors causes overdispersion, i.e., variance inflation, for measures of dependence between the two. Since then much has been written about nonsense correlations, but nearly all of it confined to the time series literature. In this paper we provide the first, to our knowledge, rigorous study of this phenomenon for other forms of (positive) dependence, specifically for Markov random fields on lattices and graphs. We consider binary and continuous random vectors and three different measures of association: correlation, covariance and the ordinary least-squares coefficient from projecting one random vector onto the other. In some settings we find variance inflation consistent with Yule’s nonsense correlation. Surprisingly, we also find variance deflation in some settings, and in others the variance is unchanged under dependence. Perhaps most notably, we find general conditions under which ordinary least-squares inference that ignores dependence is valid despite positive dependence in the regression errors, contradicting the presentation of ordinary least squares in countless textbooks and courses.

1 April 2020 in arXiv
Verified
Preprint
Open access
PDF file
BBBhaswar B. Bhattacharya
Bhaswar B. Bhattacharya
SBSohom Bhattacharya
Sohom Bhattacharya
SGShirshendu Ganguly
Shirshendu Ganguly
In this paper we consider the problem of estimating the joint upper and lower tail large deviations of the edge eigenvalues of an Erd\H{o}s-R\'enyi random graph $\mathcal{G}_{n,p}$, in the regime of $p$ where the edge of the spectrum is no longer governed by global observables, such as the number of edges, but rather by localized statistics, such as high degree vertices. Going beyond the recent developments in mean-field approximations of related problems, this paper provides a comprehensive treatment of the large deviations of the spectral edge in this entire regime, which notably includes the well studied case of constant average degree. In particular, for $r \geq 1$ fixed, we pin down the asymptotic probability that the top $r$ eigenvalues are jointly greater/less than their typical values by multiplicative factors bigger/smaller than $1$, in the regime mentioned above. The proof for the upper tail relies on a novel structure theorem, obtained by building on estimates of Krivelevich and Sudakov (2003), followed by an iterative cycle removal process, which shows, conditional on the upper tail large deviation event, with high probability the graph admits a decomposition in to a disjoint union of stars and a spectrally negligible part. On the other hand, the key ingredient in the proof of the lower tail is a Ramsey-type result which shows that if the $K$-th largest degree of a graph is not atypically small (for some large $K$ depending on $r$), then either the top eigenvalue or the $r$-th largest eigenvalue is larger than that allowed by the lower tail event on the top $r$ eigenvalues, thus forcing a contradiction. The above arguments reduce the problems to developing a large deviation theory for the extremal degrees which could be of independent interest.