4 papers
Double Preconditioning (DoPr): Optimization for Test-Time Performance, not Validation Loss
Thomas T. Zhang, Alok Shah, Yifei Zhang +3
Many modern applications of deep learning involve training a neural network via a one-step prediction loss (e.g., regression, cross-entropy), but deploy the network by rollin…
Action Chunking and Exploratory Data Collection Yield Exponential Improvements in Behavior Cloning for Continuous Control
Thomas T. Zhang, Daniel Pfrommer, Chaoyi Pan +2
This paper presents a theoretical analysis of two of the most impactful interventions in modern learning from demonstration in robotics and continuous control: the practice of acti…
On The Concurrence of Layer-wise Preconditioning Methods and Provable Feature Learning
Thomas T. Zhang, Behrad Moniri, Ansh Nagwekar +4
Layer-wise preconditioning methods are a family of memory-efficient optimization algorithms that introduce preconditioners per axis of each layer's weight tensors. These methods ha…
Guarantees for Nonlinear Representation Learning: Non-identical Covariates, Dependent Data, Fewer Samples
Thomas T. Zhang, Bruce D. Lee, Ingvar Ziemann +2
A driving force behind the diverse applicability of modern machine learning is the ability to extract meaningful features across many sources. However, many practical domains invol…