SCSabyasachi Chatterjee

Sabyasachi Chatterjee

*This is an algorithmically generated author record based on publicly available information.

Sabyasachi Chatterjee has a total of 3 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    On Estimation in Tournaments and Graphs under Monotonicity Constraints

    by Sabyasachi Chatterjee, Sumit Mukherjee

    We consider the problem of estimating the probability matrix governing a tournament or linkage in graphs from incomplete observations, under the assumption that the probability matrix satisfies natural monotonicity constraints after being permuted in both rows and columns by some latent permutation. This condition is classical in the social sciences literature (see Fishburn(1973)) and has been studied in the statistics literature in recent work (see Chatterjee (2015) and Shah et al. (2016)). In this paper, we investigate in detail a natural estimator which bypasses the need to search over all possible latent permutations and hence is computationally tractable, and derive asymptotic risk bounds for our estimator. In addition, we prove an automatic adaptation property of our estimator for several sub classes of our parameter space which are of natural interest. These sub classes include generalizations of the popular Bradley Terry Model in the Tournament case, the Beta model and Stochastic Block Model in the Graph case, and Holder smooth matrices in the tournament and graph settings.

  • Open Access

    On matrix estimation under monotonicity constraints

    by Sabyasachi Chatterjee, Adityanand Guntuboyina, Bodhisattva Sen

    We consider the problem of estimating an unknown $n_1 \times n_2$ matrix $\mathbf{\theta^*}$ from noisy observations under the constraint that $\mathbf{\theta}^*$ is nondecreasing in both rows and columns. We consider the least squares estimator (LSE) in this setting and study its risk properties. We show that the worst case risk of the LSE is $n^{-1/2}$, up to multiplicative logarithmic factors, where $n = n_1 n_2$ and that the LSE is minimax rate optimal (up to logarithmic factors). We further prove that for some special $\mathbf{\theta}^*$, the risk of the LSE could be much smaller than $n^{-1/2}$; in fact, it could even be parametric i.e., $n^{-1}$ up to logarithmic factors. Such parametric rates occur when the number of "rectangular" blocks of $\mathbf{\theta}^*$ is bounded from above by a constant. We derive, as a consequence, an interesting adaptation property of the LSE which we term variable adaptation -- the LSE performs as well as the oracle estimator when estimating a matrix that is constant along each row/column. Our proofs borrow ideas from empirical process theory and convex geometry and are of independent interest.