5 citations · 5 across the 4 of their papers we have counts for
4 papers
Realistically distributing object placements in synthetic training data improves the performance of vision-based object detection models
Setareh Dabiri, Vasileios Lioutas, Berend Zwartsenberg +8
When training object detection models on synthetic data, it is important to make the distribution of synthetic data as close as possible to the distribution of real data. We invest…
Noise Is Not the Main Factor Behind the Gap Between SGD and Adam on Transformers, but Sign Descent Might Be
Frederik Kunstner, Jacques Chen, Jonathan Wilder Lavington +1
The success of the Adam optimizer on a wide array of architectures has made it the default in settings where stochastic gradient descent (SGD) performs poorly. However, our theoret…
Target-based Surrogates for Stochastic Optimization
Jonathan Wilder Lavington, Sharan Vaswani, Reza Babanezhad +2
We consider minimizing functions for which it is expensive to compute the (possibly stochastic) gradient. Such functions are prevalent in reinforcement learning, imitation learning…
Improved Policy Optimization for Online Imitation Learning
Jonathan Wilder Lavington, Sharan Vaswani, Mark Schmidt
We consider online imitation learning (OIL), where the task is to find a policy that imitates the behavior of an expert via active interaction with the environment. We aim to bridg…