2 code implementations • 18 Sep 2017 • Bishwaranjan Bhattacharjee, Scott Boag, Chandani Doshi, Parijat Dube, Ben Herta, Vatche Ishakian, K. R. Jayaram, Rania Khalaf, Avesh Krishna, Yu Bo Li, Vinod Muthusamy, Ruchir Puri, Yufei Ren, Florian Rosenberg, Seetharami R. Seelam, Yandong Wang, Jian Ming Zhang, Li Zhang
Deep learning driven by large neural network models is overtaking traditional machine learning methods for understanding unstructured and perceptual data domains such as speech, text, and vision.
Distributed, Parallel, and Cluster Computing
no code implementations • 3 Mar 2018 • Sanghamitra Dutta, Gauri Joshi, Soumyadip Ghosh, Parijat Dube, Priya Nagpurkar
Distributed Stochastic Gradient Descent (SGD) when run in a synchronous manner, suffers from delays in waiting for the slowest learners (stragglers).
no code implementations • 30 Jul 2018 • Parijat Dube, Bishwaranjan Bhattacharjee, Elisabeth Petit-Bois, Matthew Hill
This is currently addressed by Transfer Learning where one learns the small data set as a transfer task from a larger source dataset.
no code implementations • 24 Mar 2019 • Parijat Dube, Bishwaranjan Bhattacharjee, Siyu Huo, Patrick Watson, John Kender, Brian Belgodere
Transfer learning uses trained weights from a source model as the initial weightsfor the training of a target dataset.
no code implementations • 20 Aug 2019 • Bishwaranjan Bhattacharjee, John R. Kender, Matthew Hill, Parijat Dube, Siyu Huo, Michael R. Glass, Brian Belgodere, Sharath Pankanti, Noel Codella, Patrick Watson
We use this measure, which we call "Predict To Learn" ("P2L"), in the two very different domains of images and semantic relations, where it predicts, from a set of "source" models, the one model most likely to produce effective transfer for training a given "target" model.
no code implementations • 14 Sep 2019 • K. R. Jayaram, Vinod Muthusamy, Parijat Dube, Vatche Ishakian, Chen Wang, Benjamin Herta, Scott Boag, Diana Arroyo, Asser Tantawi, Archit Verma, Falk Pollok, Rania Khalaf
This paper describes the design, implementation and our experiences with FfDL, a DL platform used at IBM.
no code implementations • 11 Feb 2020 • Sidharth Gupta, Parijat Dube, Ashish Verma
Projected Gradient Descent (PGD) based adversarial training has become one of the most prominent methods for building robust deep neural network models.
no code implementations • 31 Jul 2020 • Samuel Ackerman, Parijat Dube, Eitan Farchi
We utilize neural network embeddings to detect data drift by formulating the drift detection within an appropriate sequential decision framework.
no code implementations • 16 Dec 2020 • Samuel Ackerman, Eitan Farchi, Orna Raz, Marcel Zalmanovici, Parijat Dube
Drift is distribution change between the training and deployment data, which is concerning if model performance changes.
no code implementations • 1 Mar 2021 • Devansh Shah, Parijat Dube, Supriyo Chakraborty, Ashish Verma
We observe a significant drop in both natural and adversarial accuracies when AT is used in the federated setting as opposed to centralized training.
no code implementations • 11 Aug 2021 • Samuel Ackerman, Parijat Dube, Eitan Farchi, Orna Raz, Marcel Zalmanovici
Detecting drift in performance of Machine Learning (ML) models is an acknowledged challenge.
no code implementations • 9 Nov 2021 • Samuel Ackerman, Parijat Dube, Eitan Farchi
It is thus desirable to monitor the usage patterns and identify when the system is used in a way that was never used before.
no code implementations • 7 Jul 2022 • John R. Kender, Bishwaranjan Bhattacharjee, Parijat Dube, Brian Belgodere
Transfer learning is a deep-learning technique that ameliorates the problem of learning when human-annotated labels are expensive and limited.
no code implementations • 2 Nov 2022 • Haoze He, Parijat Dube
In this paper, we propose the (de)centralized Non-blocking SGD (Non-blocking SGD) which can address the straggler problem in a heterogeneous environment.
no code implementations • 2 Nov 2022 • Haoze He, Parijat Dube
The convergence of SGD based distributed training algorithms is tied to the data distribution across workers.
no code implementations • 13 Jun 2023 • Mujahid Ali Quidwai, Chunhui Li, Parijat Dube
The increasing reliance on large language models (LLMs) in academic writing has led to a rise in plagiarism.