← Search

Sourabh Medapati

3 accepted papers

2025

Accelerating neural network training: An analysis of the AlgoPerf competition

ICLR 2025poster

The goal of the AlgoPerf: Training Algorithms competition is to evaluate practical speed-ups in neural network training achieved solely by improving the underlying training algorithms. In the external tuning ruleset, submissions must provide workload-agnostic hyperparameter search spaces, while in t…

Cited by 0SourcePDFScholar
2025

Towards flexible perception with visual memory

ICML 2025poster

Training a neural network is a monolithic endeavor, akin to carving knowledge into stone: once the process is completed, editing the knowledge in a network is nearly impossible, since all information is distributed across the network's weights. We here explore a simple, compelling alternative by mar…

2024

Amortized Planning with Large-Scale Transformers: A Case Study on Chess

NeurIPS 2024poster

This paper uses chess, a landmark planning problem in AI, to assess transformers’ performance on a planning task where memorization is futile — even at a large scale. To this end, we release ChessBench, a large-scale benchmark dataset of 10 million chess games with legal move and value annotations (…