no code implementations • 15 Apr 2024 • Biswajit Rout, Ananya B. Sai, Arun Rajkumar
The rapid developments of various machine learning models and their deployments in several applications has led to discussions around the importance of looking beyond the accuracies of these models.
no code implementations • 15 Nov 2022 • Arnhav Datar, Arun Rajkumar, John Augustine
We first show that the popular spectral ranking based Rank-Centrality algorithm, though optimal for the BTL model, does not perform well even when a small constant fraction of the voters are Byzantine.
no code implementations • 1 Mar 2022 • Chandrashekar Lakshminarayanan, Amit Vikram Singh, Arun Rajkumar
Using the dual view, in this paper, we rethink the conventional interpretations of DNNs thereby explicitsing the implicit interpretability of DNNs.
no code implementations • NeurIPS 2021 • Vishnu Veerathu, Arun Rajkumar
Exploiting our structural characterization, we propose \texttt{PairwiseBlockRank} - a pairwise ranking algorithm for this class.
no code implementations • ICLR 2022 • Arun Rajkumar, Vishnu Veerathu, Abdul Bakey Mir
For any given tournament, we show a novel upper bound on the smallest representation dimension that depends on the least size of the number of unique nodes in any feedback arc set of the flip class associated with a tournament.
no code implementations • 13 Apr 2021 • Anant Shah, Arun Rajkumar
The learner has access to two sets of experts, one set who advise on the true cost of buying the ski and another set who advise on the length of the ski season.
no code implementations • 12 Apr 2021 • Arun Verma, Manjesh K. Hanawal, Arun Rajkumar, Raman Sankaran
The loss depends on two hidden parameters, one specific to the arm but independent of the resource allocation, and the other depends on the allocated resource.
no code implementations • 10 Jan 2020 • Sahil Manchanda, Arun Rajkumar, Simarjot Kaur, Narayanan Unny
The decision to rollout a vehicle is critical to fleet management companies as wrong decisions can lead to additional cost of maintenance and failures during journey.
1 code implementation • NeurIPS 2019 • Arun Verma, Manjesh K. Hanawal, Arun Rajkumar, Raman Sankaran
We study this novel setting by establishing its `equivalence' to Multiple-Play Multi-Armed Bandits(MP-MAB) and Combinatorial Semi-Bandits.
no code implementations • ACL 2019 • Himanshu Sharad Bhatt, Shourya Roy, Arun Rajkumar, Sriranjani Ramakrishnan
Generally it requires labeled data from the source and only unlabeled data from the target to learn such representations.
no code implementations • 11 Aug 2018 • Aadirupa Saha, Arun Rajkumar
We present a new least squares based algorithm called fBTL-LS which we show requires much lesser than $O(n\log(n))$ pairs to obtain a good ranking -- precisely our new sample complexity bound is of $O(\alpha\log \alpha)$, where $\alpha$ denotes the number of `independent items' of the set, in general $\alpha << n$.
1 code implementation • 29 May 2018 • Prateek Yadav, Madhav Nimishakavi, Naganand Yadati, Shikhar Vashishth, Arun Rajkumar, Partha Talukdar
We analyse local and global properties of graphs and demonstrate settings where LCNs tend to work better than GCNs.
no code implementations • 2 Apr 2017 • U. N. Niranjan, Arun Rajkumar, Theja Tulabandhula
The robust PCA problem, wherein, given an input data matrix that is the superposition of a low-rank matrix and a sparse matrix, we aim to separate out the low-rank and sparse components, is a well-studied problem in machine learning.
no code implementations • 22 Mar 2017 • Arun Rajkumar, Koyel Mukherjee, Theja Tulabandhula
For one of the four objectives, we show $NP$ hardness under the score structure and give a $\frac{1}{2}$ approximation algorithm for which no constant approximation was known thus far.
no code implementations • 9 Feb 2017 • U. N. Niranjan, Arun Rajkumar
We study the problem of ranking a set of items from nonactively chosen pairwise preferences where each item has feature information with it.
no code implementations • NeurIPS 2016 • Siddartha Y. Ramamohan, Arun Rajkumar, Shivani Agarwal
Recent work on deriving $O(\log T)$ anytime regret bounds for stochastic dueling bandit problems has considered mostly Condorcet winners, which do not always exist, and more recently, winners defined by the Copeland set, which do always exist.
no code implementations • NeurIPS 2014 • Arun Rajkumar, Shivani Agarwal
Here we study a general setting where costs may be linear in any suitable low-dimensional vector representation of elements of the decision space.