Skip to search formSkip to main contentSkip to account menu
  • Publications
  • Influence
Matrix Completion From a Few Entries
TLDR
An efficient algorithm is described, which is called OptSpace, that reconstructs M from |E| = O(rn) observed entries with relative root mean square error 1/2 RMSE ¿ C(¿) (nr/|E|)1/2 with probability larger than 1 - 1/n3.
View on IEEE
Matrix Completion from Noisy Entries
TLDR
This work studies a low complexity algorithm, introduced in [1], based on a combination of spectral techniques and manifold optimization, that is called here OPTSPACE, and proves performance guarantees that are order-optimal in a number of circumstances.
View PDF on arXiv
Extremal Mechanisms for Local Differential Privacy
TLDR
It is shown that for all information theoretic utility functions studied in this paper, maximizing utility is equivalent to solving a linear program, the outcome of which is the optimal staircase mechanism, which is universally optimal in the high and low privacy regimes.
View PDF on arXiv
PacGAN: The Power of Two Samples in Generative Adversarial Networks
TLDR
It is shown that packing naturally penalizes generators with mode collapse, thereby favoring generator distributions with less mode collapse during the training process, and numerical experiments suggests that packing provides significant improvements in practice as well.
View on IEEE
The Composition Theorem for Differential Privacy
TLDR
This paper proves an upper bound on the overall privacy level and construct a sequence of privatization mechanisms that achieves this bound by introducing an operational interpretation of differential privacy and the use of a data processing inequality.
View on IEEE
Rank Centrality: Ranking from Pairwise Comparisons
TLDR
Experimental evaluations on synthetic data sets generated according to the popular Bradley-Terry-Luce (BTL) model show that the proposed Rank Centrality algorithm performs as well as the maximum likelihood estimator for that model and outperforms other popular ranking algorithms.
View PDF on arXiv
Attention-based Graph Neural Network for Semi-supervised Learning
TLDR
A novel graph neural network is proposed that removes all the intermediate fully-connected layers, and replaces the propagation layers with attention mechanisms that respect the structure of the graph, and demonstrates that this approach outperforms competing methods on benchmark citation networks datasets.
View PDF on arXiv
Iterative ranking from pair-wise comparisons
TLDR
This paper proposes a novel iterative rank aggregation algorithm for discovering scores for objects from pairwise comparisons which performs as well as the Maximum Likelihood Estimator of the BTL model and outperforms a recently proposed algorithm by Ammar and Shah.
View Paper
Iterative Learning for Reliable Crowdsourcing Systems
TLDR
This paper gives a new algorithm for deciding which tasks to assign to which workers and for inferring correct answers from the workers' answers, and shows that the algorithm significantly outperforms majority voting and is asymptotically optimal through comparison to an oracle that knows the reliability of every worker.
View Paper
Budget-Optimal Task Allocation for Reliable Crowdsourcing Systems
TLDR
A new algorithm is given for deciding which tasks to assign to which workers and for inferring correct answers from the workers' answers, and it is shown that the minimum price necessary to achieve a target reliability scales in the same manner under both adaptive and nonadaptive scenarios.
View PDF on arXiv
...
...
By clicking accept or continuing to use the site, you agree to the terms outlined in our Privacy Policy, Terms of Service, and Dataset License