Search Results - "Erdil, Ege"

Explosive growth from AI automation: A review of the arguments by Erdil, Ege, Besiroglu, Tamay

“…We examine whether substantial AI automation could accelerate global economic growth by about an order of magnitude, akin to the economic growth effects of the…”
Get full text

Power Law Trends in Speedrunning and Machine Learning by Erdil, Ege, Sevilla, Jaime

“…We find that improvements in speedrunning world records follow a power law pattern. Using this observation, we answer an outstanding question from previous…”
Get full text

Data movement limits to frontier model training by Erdil, Ege, Schneider-Joseph, David

“…We present a theoretical model of distributed training, and use it to analyze how far dense and sparse training runs can be scaled. Under our baseline…”
Get full text

Algorithmic progress in computer vision by Erdil, Ege, Besiroglu, Tamay

“…We investigate algorithmic progress in image classification on ImageNet, perhaps the most well-known test bed for computer vision. We estimate a model,…”
Get full text

Estimating Idea Production: A Methodological Survey by Erdil, Ege, Besiroglu, Tamay, Ho, Anson

“…Accurately modeling the production of new ideas is crucial for innovation theory and endogenous growth models. This paper provides a comprehensive…”
Get full text

Limits to the Energy Efficiency of CMOS Microprocessors by Ho, Anson, Erdil, Ege, Besiroglu, Tamay

“…CMOS microprocessors have achieved massive energy efficiency gains but may reach limits soon. This paper presents an approach to estimating the limits on the…”
Get full text

Chinchilla Scaling: A replication attempt by Besiroglu, Tamay, Erdil, Ege, Barnett, Matthew, You, Josh

“…Hoffmann et al. (2022) propose three methods for estimating a compute-optimal scaling law. We attempt to replicate their third estimation procedure, which…”
Get full text

Algorithmic progress in language models by Ho, Anson, Besiroglu, Tamay, Erdil, Ege, Owen, David, Rahman, Robi, Guo, Zifan Carl, Atkinson, David, Thompson, Neil, Sevilla, Jaime

“…We investigate the rate at which algorithms for pre-training language models have improved since the advent of deep learning. Using a dataset of over 200…”
Get full text

FrontierMath: A Benchmark for Evaluating Advanced Mathematical Reasoning in AI by Glazer, Elliot, Erdil, Ege, Besiroglu, Tamay, Chicharro, Diego, Chen, Evan, Gunning, Alex, Olsson, Caroline Falkman, Denain, Jean-Stanislas, Ho, Anson, Santos, Emily de Oliveira, Järviniemi, Olli, Barnett, Matthew, Sandler, Robert, Vrzala, Matej, Sevilla, Jaime, Ren, Qiuyu, Pratt, Elizabeth, Levine, Lionel, Barkley, Grant, Stewart, Natalie, Grechuk, Bogdan, Grechuk, Tetiana, Enugandla, Shreepranav Varma, Wildon, Mark

“…We introduce FrontierMath, a benchmark of hundreds of original, exceptionally challenging mathematics problems crafted and vetted by expert mathematicians. The…”
Get full text