1 code implementation • 25 Jan 2022 • Komal Dhull, Steven Jecmen, Pravesh Kothari, Nihar B. Shah
Finally, we evaluate the methods on a dataset from conference peer review.
no code implementations • 6 May 2020 • Ainesh Bakshi, Pravesh Kothari
Concretely, our algorithm takes input an $\epsilon$-corrupted sample from a $k$-GMM and whp in $d^{\text{poly}(k/\eta)}$ time, outputs an approximate clustering that misclassifies at most $k^{O(k)}(\epsilon+\eta)$ fraction of the points whenever every pair of mixture components are separated by $1-\exp(-\text{poly}(k/\eta)^k)$ in total variation (TV) distance.
no code implementations • NeurIPS 2014 • Deeparnab Chakrabarty, Prateek Jain, Pravesh Kothari
In 1976, Wolfe proposed an algorithm to find the minimum Euclidean norm point in a polytope, and in 1980, Fujishige showed how Wolfe's algorithm can be used for SFM.
no code implementations • 27 May 2014 • Vitaly Feldman, Pravesh Kothari
This directly gives an agnostic learning algorithm for disjunctions on symmetric distributions that runs in time $n^{O( \log{(1/\epsilon)})}$.
no code implementations • 18 Apr 2014 • Vitaly Feldman, Pravesh Kothari, Jan Vondrák
Previous techniques considered stronger $\ell_2$ approximation and proved nearly tight bounds of $\Theta(1/\epsilon^{2})$ on the degree and $2^{\Theta(1/\epsilon^2)}$ on the number of variables.
no code implementations • 8 Apr 2013 • Vitaly Feldman, Pravesh Kothari
As an application of our learning results, we give simple differentially-private algorithms for releasing monotone conjunction counting queries with low average error.
no code implementations • 2 Apr 2013 • Vitaly Feldman, Pravesh Kothari, Jan Vondrak
We show that these structural results can be exploited to give an attribute-efficient PAC learning algorithm for submodular functions running in time $\tilde{O}(n^2) \cdot 2^{O(1/\epsilon^{4})}$.