27 citations · 78 across the 12 of their papers we have counts for
7 papers · 1 filter
Accelerating Parallel Stochastic Gradient Descent via Non-blocking Mini-batches
Haoze He, Parijat Dube
SOTA decentralized SGD algorithms can overcome the bandwidth bottleneck at the parameter server by using communication collectives like Ring All-Reduce for synchronization. While t…
RCD-SGD: Resource-Constrained Distributed SGD in Heterogeneous Environment via Submodular Partitioning
Haoze He, Parijat Dube
The convergence of SGD based distributed training algorithms is tied to the data distribution across workers. Standard partitioning techniques try to achieve equal-sized partitions…
G2L: A Geometric Approach for Generating Pseudo-labels that Improve Transfer Learning
John R. Kender, Bishwaranjan Bhattacharjee, Parijat Dube +1
Transfer learning is a deep-learning technique that ameliorates the problem of learning when human-annotated labels are expensive and limited. In place of such labels, it uses inst…
Machine Learning Model Drift Detection Via Weak Data Slices
Samuel Ackerman, Parijat Dube, Eitan Farchi +2
Detecting drift in performance of Machine Learning (ML) models is an acknowledged challenge. For ML models to become an integral part of business applications it is essential to de…
Adversarial training in communication constrained federated learning
Devansh Shah, Parijat Dube, Supriyo Chakraborty +1
Federated learning enables model training over a distributed corpus of agent data. However, the trained model is vulnerable to adversarial examples, designed to elicit misclassific…
Improving the affordability of robustness training for DNNs
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. However, the computational…
P2L: Predicting Transfer Learning for Images and Semantic Relations
Bishwaranjan Bhattacharjee, John R. Kender, Matthew Hill +7
Transfer learning enhances learning across tasks, by leveraging previously learned representations -- if they are properly chosen. We describe an efficient method to accurately est…