1 citations · 1 across the 8 of their papers we have counts for
10 papers
Is Spectral Self-Supervised Learning a Minimax Optimal Method of Density Ratio Estimation?
Hiroki Waida, Takafumi Kanamori
Spectral self-supervised learning is a method of density ratio estimation for the setting in which only samples drawn from the joint density of the numerator are available. The met…
Selecting Repetition Counts Across Model Scales in Data-Constrained Pretraining
Ziyue WANG, T. Kanamori
The repetition count that works best for a small language model may not remain best at a larger scale. We study this effect in pretraining with a finite target corpus mixed with ge…
Should the Boundary Term Be Learned in Reflected Diffusion? Conormal Trace and Reflection Masking
Ziyue Wang, Takafumi Kanamori
We study score learning for reflected diffusion on bounded domains. Reflection keeps trajectories feasible but does not ensure that the learned score satisfies the boundary behavio…
Fast boundary-aware spatial intensity estimation on complex domains
Takumi Nakagawa, Kōsaku Takanashi, Kenichiro McAlinn +1
Spatial intensity maps are routinely used to summarize point patterns on geographically constrained regions, such as islands, coastlines, watersheds, ecological reserves, and admin…
Generalized Distribution-Free Semi-Supervised Learning with Risk Rewrite
Yushi Hirose, Hiroo Irobe, Takafumi Kanamori
Typical semi-supervised learning (SSL) methods rely on distributional assumptions, and their performance degrades when these are violated. While PNU learning, a risk rewriting meth…
Distributional Spectral Diagnostics for Localizing Grokking Transitions
Ziyue Wang, Yufeng Ying, Takafumi Kanamori
In grokking, a model first fits the training data while test accuracy remains low, and only later begins to generalize. We ask whether this transition can be localized from observe…
TULiP: Test-time Uncertainty Estimation via Linearization and Weight Perturbation
Yuhui Zhang, Dongshen Wu, Yuichiro Wada +1
A reliable uncertainty estimation method is the foundation of many modern out-of-distribution (OOD) detectors, which are critical for safe deployments of deep learning models in th…
Statistical learnability of smooth boundaries via pairwise binary classification with deep ReLU networks
Hiroki Waida, Takafumi Kanamori
The topic of nonparametric estimation of smooth boundaries is extensively studied in the conventional setting where pairs of single covariate and response variable are observed. Ho…
Scaling-based Data Augmentation for Generative Models and its Theoretical Extension
Yoshitaka Koike, Takumi Nakagawa, Hiroki Waida +1
This paper studies stable learning methods for generative models that enable high-quality data generation. Noise injection is commonly used to stabilize learning. However, selectin…
Robust VAEs via Generating Process of Noise Augmented Data
Hiroo Irobe, Wataru Aoki, Kimihiro Yamazaki +5
Advancing defensive mechanisms against adversarial attacks in generative models is a critical research topic in machine learning. Our study focuses on a specific type of generative…