16 citations · 33 across the 9 of their papers we have counts for
9 papers
Simulating Unified Tensor Resharding in heterogeneous AI systems
Sumit Kumar, Sayantan Dasgupta, Kushal Mitra +6
State-of-the-art AI training simulators assume homogeneous compute and network infrastructure. However, real-world training infrastructure is becoming increasingly heterogeneous si…
Don't Ignore the Tail: Decoupling top-K Probabilities for Efficient Language Model Distillation
Sayantan Dasgupta, Trevor Cohn, Timothy Baldwin
The core learning signal used in language model distillation is the standard Kullback-Leibler (KL) divergence between the student and teacher distributions. Traditional KL divergen…
A framework for predicting, interpreting, and improving Learning Outcomes
Chintan Donda, Sayan Dasgupta, Soma S Dhavala +2
It has long been recognized that academic success is a result of both cognitive and non-cognitive dimensions acting together. Consequently, any intelligent learning platform design…
Impact of a colored vector resonance on the collider constraints for top-like top partner
Sayan Dasgupta, Santosh Kumar Rai, Tirtha Sankar Ray
In this work we reappraise the collider constraints from leptonic final states on the vectorlike colored top partners taking into account the impact of exotic colored vector resona…
On Data Enriched Logistic Regression
Cheng Zheng, Sayan Dasgupta, Yuxiang Xie +2
Biomedical researchers usually study the effects of certain exposures on disease risks among a well-defined population. To achieve this goal, the gold standard is to design a trial…
Status of Flavour Maximal Non-minimal Universal Extra Dimension
Sayan Dasgupta, Ujjal Kumar Dey, Tapoja Jha +1
In this paper we consider an compactified flat extra dimensional scenario where all the standard model states can access the bulk and have generalised brane lo…
Multi-Label Learning with Provable Guarantee
Sayantan Dasgupta
Here we study the problem of learning labels for large text corpora where each text can be assigned a variable number of labels. The problem might seem trivial when the label dimen…
Seeding K-Means using Method of Moments
Sayantan Dasgupta
K-means is one of the most widely used algorithms for clustering in Data Mining applications, which attempts to minimize the sum of the square of the Euclidean distance of the poin…
Fast Collaborative Filtering from Implicit Feedback with Provable Guarantees
Sayantan Dasgupta
Building recommendation algorithms is one of the most challenging tasks in Machine Learning. Although most of the recommendation systems are built on explicit feedback available fr…