no code implementations • NeurIPS 2023 • Tzu-Heng Huang, Harit Vishwakarma, Frederic Sala
Organizations typically train large models individually.
1 code implementation • 24 Nov 2022 • Harit Vishwakarma, Nicholas Roberts, Frederic Sala
Weak supervision (WS) is a rich set of techniques that produce pseudolabels by aggregating easily obtained but potentially noisy label estimates from a variety of sources.
2 code implementations • NeurIPS 2023 • Harit Vishwakarma, Heguang Lin, Frederic Sala, Ramya Korlakai Vinayak
Given the long shelf-life and diverse usage of the resulting datasets, understanding when the data obtained by such auto-labeling systems can be relied on is crucial.
no code implementations • ICLR 2022 • Changho Shin, Winfred Li, Harit Vishwakarma, Nicholas Roberts, Frederic Sala
We apply this technique to important problems previously not tackled by WS frameworks including learning to rank, regression, and learning in hyperbolic space.
1 code implementation • NeurIPS 2020 • Ankit Pensia, Shashank Rajput, Alliot Nagle, Harit Vishwakarma, Dimitris Papailiopoulos
We show that any target network of width $d$ and depth $l$ can be approximated by pruning a random network that is a factor $O(log(dl))$ wider and twice as deep.
2 code implementations • NeurIPS 2020 • Hongyi Wang, Kartik Sreenivasan, Shashank Rajput, Harit Vishwakarma, Saurabh Agarwal, Jy-yong Sohn, Kangwook Lee, Dimitris Papailiopoulos
Due to its decentralized nature, Federated Learning (FL) lends itself to adversarial attacks in the form of backdoors during training.
1 code implementation • 14 Jun 2020 • Ankit Pensia, Shashank Rajput, Alliot Nagle, Harit Vishwakarma, Dimitris Papailiopoulos
We show that any target network of width $d$ and depth $l$ can be approximated by pruning a random network that is a factor $O(\log(dl))$ wider and twice as deep.
1 code implementation • NeurIPS 2019 • Dinesh Garg, Shajith Ikbal Mohamed, Santosh K. Srivastava, Harit Vishwakarma, Hima Karanam, L. Venkata Subramaniam
Statistical Relational Learning (SRL) methods are the most widely used techniques to generate distributional representations of the symbolic Knowledge Bases (KBs).
no code implementations • 11 Dec 2017 • Rakesh R Pimplikar, Kushal Mukherjee, Gyana Parija, Harit Vishwakarma, Ramasuri Narayanam, Sarthak Ahuja, Rohith D Vallam, Ritwik Chaudhuri, Joydeep Mondal
Research in Artificial Intelligence is breaking technology barriers every day.