Výsledky vyhledávání - "Singh, Anima"

Report

Density Weighting for Multi-Interest Personalized Recommendation

Autor: Mehta, Nikhil, Singh, Anima, Yi, Xinyang, Jain, Sagar, Hong, Lichan, Chi, Ed H.

Using multiple user representations (MUR) to model user behavior instead of a single user representation (SUR) has been shown to improve personalization in recommendation systems. However, the performance gains observed with MUR can be sensitive to t

Externí odkaz: http://arxiv.org/abs/2308.01563

Zobrazit plný text záznamu

Report

Better Generalization with Semantic IDs: A Case Study in Ranking for Recommendations

Autor: Singh, Anima, Vu, Trung, Mehta, Nikhil, Keshavan, Raghunandan, Sathiamoorthy, Maheswaran, Zheng, Yilin, Hong, Lichan, Heldt, Lukasz, Wei, Li, Tandon, Devansh, Chi, Ed H., Yi, Xinyang

Randomly-hashed item ids are used ubiquitously in recommendation models. However, the learned representations from random hashing prevents generalization across similar items, causing problems of learning unseen and long-tail items, especially when i

Externí odkaz: http://arxiv.org/abs/2306.08121

Zobrazit plný text záznamu

Report

Recommender Systems with Generative Retrieval

Autor: Rajput, Shashank, Mehta, Nikhil, Singh, Anima, Keshavan, Raghunandan H., Vu, Trung, Heldt, Lukasz, Hong, Lichan, Tay, Yi, Tran, Vinh Q., Samost, Jonah, Kula, Maciej, Chi, Ed H., Sathiamoorthy, Maheswaran

Modern recommender systems perform large-scale retrieval by first embedding queries and item candidates in the same unified space, followed by approximate nearest neighbor search to select top candidates given a query embedding. In this paper, we pro

Externí odkaz: http://arxiv.org/abs/2305.05065

Zobrazit plný text záznamu

Report

Understanding and Improving Knowledge Distillation

Autor: Tang, Jiaxi, Shivanna, Rakesh, Zhao, Zhe, Lin, Dong, Singh, Anima, Chi, Ed H., Jain, Sagar

Knowledge Distillation (KD) is a model-agnostic technique to improve model quality while having a fixed capacity budget. It is a commonly used technique for model compression, where a larger capacity teacher model with better quality is used to train

Externí odkaz: http://arxiv.org/abs/2002.03532

Zobrazit plný text záznamu

Dissertation/ Thesis

Exploiting hierarchical and temporal information in building predictive models from EHR data

Autor: Singh, Anima, Ph. D. Massachusetts Institute of Technology

Thesis: Ph. D., Massachusetts Institute of Technology, Department of Electrical Engineering and Computer Science, 2015.
This electronic version was submitted by the student author. The certified thesis is available in the Institute Archives and

Externí odkaz: http://hdl.handle.net/1721.1/99783

Zobrazit plný text záznamu

Dissertation/ Thesis

Risk stratification of cardiovascular patients using a novel classification tree induction algorithm with non-symmetric entropy measures

Autor: Singh, Anima, Ph. D. Massachusetts Institute of Technology

Thesis (S.M.)--Massachusetts Institute of Technology, Dept. of Electrical Engineering and Computer Science, 2011.
Cataloged from PDF version of thesis.
Includes bibliographical references (p. 95-100).
Risk stratification allows clinici

Externí odkaz: http://hdl.handle.net/1721.1/64601

Zobrazit plný text záznamu