5 papers
Stabilizing Private LASSO under Heterogeneous Covariates via Anisotropic Objective Perturbation
Haruka Tanzawa, Ayaka Sakata
We study high-dimensional LASSO under differential privacy via objective perturbation with heterogeneous covariate scales. In practical scenarios, covariates often exhibit diverse…
Privacy-Accuracy Trade-offs in High-Dimensional LASSO under Perturbation Mechanisms
Ayaka Sakata, Haruka Tanzawa
We study privacy-preserving sparse linear regression in the high-dimensional regime, focusing on the LASSO estimator. We analyze two widely used mechanisms for differential privacy…
Perfect reconstruction of sparse signals using nonconvexity control and one-step RSB message passing
Xiaosi Gu, Ayaka Sakata, Tomoyuki Obuchi
We consider sparse signal reconstruction via minimization of the smoothly clipped absolute deviation (SCAD) penalty, and develop one-step replica-symmetry-breaking (1RSB) extension…
The Effect of Optimal Self-Distillation in Noisy Gaussian Mixture Model
Kaito Takanami, Takashi Takahashi, Ayaka Sakata
Self-distillation (SD), a technique where a model improves itself using its own predictions, has attracted attention as a simple yet powerful approach in machine learning. Despite…
High-Dimensional Learning Dynamics of Quantized Models with Straight-Through Estimator
Yuma Ichikawa, Shuhei Kashiwamura, Ayaka Sakata
Quantized neural network training optimizes a discrete, non-differentiable objective. The straight-through estimator (STE) enables backpropagation through surrogate gradients and i…