activity
20232026
most citedRobust VAEs via Generating Process of Noise Augmented Data

1 citations · 1 across the 6 of their papers we have counts for

collaborators

6 papers

stat.ME2026

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…

cs.LG2026

PHOTON: Hierarchical Autoregressive Modeling for Lightspeed and Memory-Efficient Language Generation

Yuma Ichikawa, Naoya Takagi, Takumi Nakagawa +2

Transformers operate as horizontal token-by-token scanners; at each generation step, attending to an ever-growing sequence of token-level states. This access pattern increases pref…

stat.ML2024

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…

cs.LG2024★ 1 cited

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…

stat.ML2023

Denoising Cosine Similarity: A Theory-Driven Approach for Efficient Representation Learning

Takumi Nakagawa, Yutaro Sanada, Hiroki Waida +5

Representation learning has been increasing its impact on the research and practice of machine learning, since it enables to learn representations that can apply to various downstr…

cs.LG2023

Towards Understanding the Mechanism of Contrastive Learning via Similarity Structure: A Theoretical Analysis

Hiroki Waida, Yuichiro Wada, Léo Andéol +3

Contrastive learning is an efficient approach to self-supervised representation learning. Although recent studies have made progress in the theoretical understanding of contrastive…