From Stability to Chaos: Analyzing Gradient Descent Dynamics in Quadratic Regression

no code implementations • 2 Oct 2023 • Xuxing Chen, Krishnakumar Balasubramanian, Promit Ghosal, Bhavya Agrawalla

We conduct a comprehensive investigation into the dynamics of gradient descent using large-order constant step-sizes in the context of quadratic regression models.

regression Retrieval

DISeR: Designing Imaging Systems with Reinforcement Learning

no code implementations • ICCV 2023 • Tzofi Klinghoffer, Kushagra Tiwary, Nikhil Behari, Bhavya Agrawalla, Ramesh Raskar

In this paper, we formulate these four building blocks of imaging systems as a context-free grammar (CFG), which can be automatically searched over with a learned camera designer to jointly optimize the imaging system with task-specific perception models.

Autonomous Vehicles Depth Estimation +1

Statistical Inference for Linear Functionals of Online SGD in High-dimensional Linear Regression

no code implementations • 20 Feb 2023 • Bhavya Agrawalla, Krishnakumar Balasubramanian, Promit Ghosal

In order to use the developed result in practice, we further develop an online approach for estimating the expectation and the variance terms appearing in the CLT, and establish high-probability bounds for the developed online estimator.

Learning Theory