no code implementations • LREC 2022 • William Britton, Somdeb Sarkhel, Deepak Venugopal
Visual Question Answering (VQA) is a challenge problem that can advance AI by integrating several important sub-disciplines including natural language understanding and computer vision.
1 code implementation • 5 Jan 2024 • Abisha Thapa Magar, Anup Shakya, Somdeb Sarkhel, Deepak Venugopal
Explanations on relational data are hard to verify since the explanation structures are more complex (e. g. graphs).
no code implementations • 13 Dec 2023 • Anup Shakya, Abisha Thapa Magar, Somdeb Sarkhel, Deepak Venugopal
The standard approach to verify representations learned by Deep Neural Networks is to use them in specific tasks such as classification or regression, and measure their performance based on accuracy in such tasks.
no code implementations • 20 Oct 2023 • Yuchen Zhuang, Xiang Chen, Tong Yu, Saayan Mitra, Victor Bursztyn, Ryan A. Rossi, Somdeb Sarkhel, Chao Zhang
It formulates the entire action space as a decision tree, where each node represents a possible API function call involved in a solution plan.
no code implementations • 28 Nov 2022 • Jiehao Liang, Somdeb Sarkhel, Zhao Song, Chenbo Yin, Junze Yin, Danyang Zhuo
We propose a new algorithm \textsc{FastKmeans++} that only takes in $\widetilde{O}(nd + nk^2)$ time, in total.
no code implementations • 31 Mar 2020 • Aritra Ghosh, Saayan Mitra, Somdeb Sarkhel, Viswanathan Swaminathan
Earlier works on optimal bidding strategy apply model-based batch reinforcement learning methods which can not generalize to unknown budget and time constraint.
no code implementations • 18 Jan 2020 • Aritra Ghosh, Saayan Mitra, Somdeb Sarkhel, Jason Xie, Gang Wu, Viswanathan Swaminathan
The highest bidding advertiser wins but pays only the second-highest bid (known as the winning price).
no code implementations • 16 Jan 2020 • Ryan Rossi, Somdeb Sarkhel, Nesreen Ahmed
We propose causal inference models for this problem that leverage both the graph topology and time-series to accurately estimate local causal effects of nodes.
no code implementations • NeurIPS 2015 • Somdeb Sarkhel, Parag Singla, Vibhav G. Gogate
A key advantage of these lifted algorithms is that they have much smaller computational complexity than propositional algorithms when symmetries are present in the MLN and these symmetries can be detected using lifted inference rules.
no code implementations • NeurIPS 2014 • Somdeb Sarkhel, Deepak Venugopal, Parag Singla, Vibhav G. Gogate
In this paper, we present a new approach for lifted MAP inference in Markov logic networks (MLNs).