Megh Thakkar

Megh Thakkar

Auto-generated profile, based on publicly available information

Megh Thakkar

BITS, Pilani, Pilani, India

Research Focus & Metrics

Academic Career Length

4Years (2023-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
18 July 2023
Verified
Conference Paper
Open access
PCParth Chhabra
Parth Chhabra
ANAtula Tejaswi Neerkaje
Atula Tejaswi Neerkaje
SAShivam Agarwal
Shivam Agarwal
RSRamit Sawhney
Ramit Sawhney
MTMegh Thakkar
Megh Thakkar
SCSudheer Chava
Sudheer Chava
Mixup is an efficient data augmentation technique, which improves generalization by interpolating random examples. While numerous approaches have been developed for Mixup in the Euclidean and in the hyperbolic space, they do not fully use the intrinsic properties of the examples, i.e., they manually set the geometry (Euclidean or hyperbolic) based on the overall dataset, which may be sub-optimal since each example may require a different geometry. We propose DynaMix, a framework that automatically selects an example-specific geometry and performs Mixup between the different geometries to improve training dynamics and generalization. Through extensive experiments in image and text modalities we show that DynaMix outperforms state-of-the-art methods over six downstream applications. We find that DynaMix is more useful in low-resource and semi-supervised settings likely because it displays a probabilistic view of the geometry.