activity
20242026
collaborators
Showing stat.MLShow all

7 papers · 1 filter

stat.ML2026

SGD Provably Prioritizes a Shortcut Spurious Feature in the XOR Model

Tyler LaBonte, Vidya Muthukumar

Neural networks are known to be susceptible to over-reliance on spurious correlations. However, the precise mechanism by which models exploit shortcut features is not fully underst…

stat.ML2026

How Does the ReLU Activation Affect the Implicit Bias of Gradient Descent on High-dimensional Neural Network Regression?

Kuo-Wei Lai, Guanghui Wang, Molei Tao +1

Overparameterized ML models, including neural networks, typically induce underdetermined training objectives with multiple global minima. The implicit bias refers to the limiting g…

stat.ML2025

A general technique for approximating high-dimensional empirical kernel matrices

Chiraag Kaushik, Justin Romberg, Vidya Muthukumar

We present simple, user-friendly bounds for the expected operator norm of a random kernel matrix under general conditions on the kernel function . Our approach uses…

stat.ML2025

General Loss Functions Lead to (Approximate) Interpolation in High Dimensions

Kuo-Wei Lai, Vidya Muthukumar

We provide a unified framework that applies to a general family of convex losses across binary and multiclass settings in the overparameterized regime to approximately characterize…

stat.ML2025

Estimating stationary mass, frequency by frequency

Milind Nakul, Vidya Muthukumar, Ashwin Pananjady

Suppose we observe a trajectory of length from an exponentially -mixing stochastic process over a finite but potentially large state space. We consider the problem of estim…

stat.ML2025

Task Shift: From Classification to Regression in Overparameterized Linear Models

Tyler LaBonte, Kuo-Wei Lai, Vidya Muthukumar

Modern machine learning methods have recently demonstrated remarkable capability to generalize under task shift, where latent knowledge is transferred to a different, often more di…