Abstract

List of Posters:

• Measuring Training Variability Using Robust Statistics, Sinjini Banerjee
• Implicit Bias of SGD in L2-regularized linear DNNs: One-way Jumps from High to Low Rank, Zihan Wang
• Approximating Eigenvalues of Symmetric Matrices using Matrix-vector Query Algorithms, Archan Ray
• Understanding Adversarial Risks, Natalie Frank
• Error in Variables Regression: Benigh Overfitting, Covariate shifts, and Underparameterized Double Descent, Rishi Sonthalia
• Fiber Bundle Morphisms as a Framework for Modeling Many-to-Many Maps, Lizzy Coda
• Bias Introduced by Machine Processing, Max Vargas
• Uncertainty Quantification for Iterative Algorithms in Linear Models with Application to Early Stopping, Kai Tan
• MORALS: Analysis of High-Dimensional Robot Controllers via Topological Tools in a Latent Space, Ewerton Rocha Vieira
• Scaling and Renormalization in High-dimensional Regression, Jacob Zavatone-Veth
• Theory of In-Context Learning for Regression with Linear Attention, Mary Letey
• Unlocking Exact Recovery in Semi-Supervised Learning: Analysis of Spectral Method and Graph Convolution Network, Haixiao Wang
• A Dynamical Model of Neural Scaling Laws, Alexander Atanasov

Poster Session Abstracts