12 citations · 12 across the 5 of their papers we have counts for
6 papers
DASH: Fast, Valid Counterfactuals for Deep Networks via Batched Directional Search
Shraman Pal, Gabriel Medeiros, Clayton Escouper das Chagas +1
Counterfactual explanations are most useful when they can be generated with low latency, remain close to the factual input, and satisfy input-domain, categorical, and actionability…
DisjunctiveNet: Neural Symbolic Learning via Differentiable Convexified Optimization Layers
Shraman Pal, Can Li
Many learning tasks in science and engineering are characterized by sparse datasets, which limits the effectiveness of purely data-driven approaches. At the same time, these proble…
SafeOR-Gym: A Benchmark Suite for Safe Reinforcement Learning Algorithms on Practical Operations Research Problems
Asha Ramanujam, Adam Elyoumi, Hao Chen +5
Most existing safe reinforcement learning (RL) benchmarks focus on robotics and control tasks, offering limited relevance to high-stakes domains that involve structured constraints…
Improving Question Answering with Generation of NQ-like Questions
Saptarashmi Bandyopadhyay, Shraman Pal, Hao Zou +2
Question Answering (QA) systems require a large amount of annotated data which is costly and time-consuming to gather. Converting datasets of existing QA benchmarks are challenging…
Server-Side Local Gradient Averaging and Learning Rate Acceleration for Scalable Split Learning
Shraman Pal, Mansi Uniyal, Jihong Park +5
In recent years, there have been great advances in the field of decentralized learning with private data. Federated learning (FL) and split learning (SL) are two spearheads possess…
Leveraging recent advances in Pre-Trained Language Models forEye-Tracking Prediction
Varun Madhavan, Aditya Girish Pawate, Shraman Pal +1
Cognitively inspired Natural Language Pro-cessing uses human-derived behavioral datalike eye-tracking data, which reflect the seman-tic representations of language in the humanbrai…