collaborators

8 papers

cs.CV2025

Towards flexible perception with visual memory

Robert Geirhos, Priyank Jaini, Austin Stone +5

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 hard, since all infor…

cs.LG2025

Benchmarking Neural Network Training Algorithms

George E. Dahl, Frank Schneider, Zachary Nado +22

Training algorithms, broadly construed, are an essential part of every deep learning pipeline. Training algorithm improvements that speed up training across a wide variety of workl…

cs.LG2025

How far away are truly hyperparameter-free learning algorithms?

Priya Kasimbeg, Vincent Roulet, Naman Agarwal +4

Despite major advances in methodology, hyperparameter tuning remains a crucial (and expensive) part of the development of machine learning systems. Even ignoring architectural choi…

cs.LG2025

Learning by solving differential equations

Benoit Dherin, Michael Munn, Hanna Mazzawi +3

Modern deep learning algorithms use variations of gradient descent as their main learning methods. Gradient descent can be understood as the simplest Ordinary Differential Equation…

cs.LG2025

Training neural networks faster with minimal tuning using pre-computed lists of hyperparameters for NAdamW

Sourabh Medapati, Priya Kasimbeg, Shankar Krishnan +2

If we want to train a neural network using any of the most popular optimization algorithms, we are immediately faced with a dilemma: how to set the various optimization and regular…

cs.LG2025

Accelerating Neural Network Training: An Analysis of the AlgoPerf Competition

Priya Kasimbeg, Frank Schneider, Runa Eschenhagen +11

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 algorit…