Amarjit Budhiraja — accepted AI-conference papers

2023

Does Momentum Help in Stochastic Optimization? A Sample Complexity Analysis.

Swetha Ganesh, Rohan Deb, Gugan Thoppe, Amarjit Budhiraja

UAI 2023poster

Stochastic Heavy Ball (SHB) and Nesterov’s Accelerated Stochastic Gradient (ASG) are popular momentum methods in optimization. While the benefits of these acceleration ideas in deterministic settings are well understood, their advantages in stochastic optimization are unclear. Several works have rec…

Cited by 4 Source ↗PDF ↗Scholar ↗

2020

Augmenting Molecular Images with Vector Representations as a Featurization Technique for Drug Classification

Daniel de Marchi, Amarjit Budhiraja

ICASSP 2020accepted

One of the key steps in building deep learning systems for drug classification and generation is the choice of featurization for the molecules. Previous featurization methods have included molecular images, binary strings, graphs, and SMILES strings. This paper proposes the creation of molecular ima…

Cited by 0 Source ↗Scholar ↗