no code implementations • 16 Apr 2024 • Chung-Yiu Yau, Hoi-To Wai, Parameswaran Raman, Soumajyoti Sarkar, Mingyi Hong
We follow the global contrastive learning loss as introduced in SogCLR, and propose EMC$^2$ which utilizes an adaptive Metropolis-Hastings subroutine to generate hardness-aware negative samples in an online fashion during the optimization.
no code implementations • 1 Oct 2023 • Soumajyoti Sarkar, Leonard Lausen
Tables stored in databases and tables which are present in web pages and articles account for a large part of semi-structured data that is available on the internet.
1 code implementation • NeurIPS 2023 • Pei Chen, Soumajyoti Sarkar, Leonard Lausen, Balasubramaniam Srinivasan, Sheng Zha, Ruihong Huang, George Karypis
Language models pretrained on large collections of tabular data have demonstrated their effectiveness in several downstream tasks.
no code implementations • 9 May 2023 • Soumajyoti Sarkar
Decentralized multi-agent reinforcement learning (MARL) algorithms have become popular in the literature since it allows heterogeneous agents to have their own reward functions as opposed to canonical multi-agent Markov Decision Process (MDP) settings which assume common reward functions over all agents.
no code implementations • 8 Nov 2022 • Soumajyoti Sarkar, Kaixiang Lin, Sailik Sengupta, Leonard Lausen, Sheng Zha, Saab Mansour
While prior research studies have tried to adapt these multilingual models for dialectal variants of Arabic, it still remains a challenging problem owing to the lack of sufficient monolingual dialectal data and parallel translation data of such dialectal variants.
no code implementations • 6 May 2021 • Soumajyoti Sarkar
We study investment designs in two sided platforms using matching markets when the investors or lenders also face restrictions on the investments based on borrower preferences.
no code implementations • 30 Oct 2020 • Soumajyoti Sarkar
Motivated by recent applications of sequential decision making in matching markets, in this paper we attempt at formulating and abstracting market designs for P2P lending.
no code implementations • 20 Jun 2020 • Soumajyoti Sarkar, Hamidreza Alvari
We find that the influence from economic factors and loan attributes can have substantially different roles to play for different sectors in achieving faster funding.