37 citations · 137 across the 20 of their papers we have counts for
7 papers · 1 filter
Combining Gradients and Probabilities for Heterogeneous Approximation of Neural Networks
Elias Trommer, Bernd Waschneck, Akash Kumar
This work explores the search for heterogeneous approximate multiplier configurations for neural networks that produce high accuracy and low energy consumption. We discuss the vali…
Bounding the List Color Function Threshold from Above
Hemanshu Kaul, Akash Kumar, Andrew Liu +5
The chromatic polynomial of a graph , denoted , is equal to the number of proper -colorings of for each . In 1990, Kostochka and Sidorenko intro…
Approximating Dasgupta Cost in Sublinear Time from a Few Random Seeds
Michael Kapralov, Akash Kumar, Silvio Lattanzi +2
Testing graph cluster structure has been a central object of study in property testing since the foundational work of Goldreich and Ron [STOC'96] on expansion testing, i.e. the pro…
Exact recovery algorithm for Planted Bipartite Graph in Semi-random Graphs
Akash Kumar, Anand Louis, Rameesh Paul
The problem of finding the largest induced balanced bipartite subgraph in a given graph is NP-hard. This problem is closely related to the problem of finding the smallest Odd Cycle…
Video Action Detection: Analysing Limitations and Challenges
Rajat Modi, Aayush Jung Rana, Akash Kumar +4
Beyond possessing large enough size to feed data hungry machines (eg, transformers), what attributes measure the quality of a dataset? Assuming that the definitions of such attribu…
End-to-End Semi-Supervised Learning for Video Action Detection
Akash Kumar, Yogesh Singh Rawat
In this work, we focus on semi-supervised learning for video action detection which utilizes both labeled as well as unlabeled data. We propose a simple end-to-end consistency base…