9 papers
Training and Evaluating Diffusion Policies with Long Context Lengths
Abhinav Agarwal, Adam Wei, Taylan Kargin +6
Imitation learning has enabled highly-dexterous robotic manipulation from RGB observations. Policies trained with these methods, however, typically condition robot actions on only…
Semidefinite Relaxations for Collision-Free Motion Planning
Bernhard Paus Graesdal, Alexandre Amice, Pablo A. Parrilo +1
We study semidefinite relaxations for collision-free motion planning. We focus on a point robot moving from start to goal through spherical obstacles in , subject to…
Spectral Scaling Laws of Muon
Gagik Magakyan, Pablo Parrilo, Asuman Ozdaglar
Orthonormalized update rules have rapidly become a leading choice of optimizer for training large language models, with recent open-source state-of-the-art models adopting Muon. To…
Stepsize Hedging: an Alternative Mechanism for Accelerating Gradient Descent
Jason M. Altschuler, Pablo A. Parrilo
Can gradient descent be accelerated by just choosing better stepsizes? Surprisingly, the answer is yes. This short expository article provides an accessible introduction to this ph…
Collaborative and Efficient Fine-tuning: Leveraging Task Similarity
Gagik Magakyan, Amirhossein Reisizadeh, Chanwoo Park +2
Adaptability has been regarded as a central feature in the foundation models, enabling them to effectively acclimate to unseen downstream tasks. Parameter-efficient fine-tuning met…
Acceleration by Random Stepsizes: Hedging, Equalization, and the Arcsine Stepsize Schedule
Jason M. Altschuler, Pablo A. Parrilo
We show that for separable convex optimization, random stepsizes fully accelerate Gradient Descent. Specifically, using inverse stepsizes i.i.d. from the Arcsine distribution impro…