3 papers
math.OC2026
Parameter Tuning with Generalization Guarantees for GPU-Accelerated Linear Programming
Siddharth Prasad, Dravyansh Sharma
Recent research has developed practical, parallelizable first-order methods for large scale linear programming, but performance is highly dependent on hyperparameter selection. We…
cs.LG2025
Gradient Descent with Provably Tuned Learning-rate Schedules
Dravyansh Sharma
Gradient-based iterative optimization methods are the workhorse of modern machine learning. They crucially rely on careful tuning of parameters like learning rate and momentum. How…
cs.LG2025
Conservative classifiers do consistently well with improving agents: characterizing statistical and online learning
Dravyansh Sharma, Alec Sun
Machine learning is now ubiquitous in societal decision-making, for example in evaluating job candidates or loan applications, and it is increasingly important to take into account…