20 citations · 48 across the 20 of their papers we have counts for
10 papers · 1 filter
Relative Density Ratio Optimization for Stable and Statistically Consistent Model Alignment
Hiroshi Takahashi, Tomoharu Iwata, Atsutoshi Kumagai +4
Aligning language models with human preferences is essential for ensuring their safety and reliability. Although most existing approaches assume specific human preference models su…
Test-time reward-guided alignment of language models by importance sampling on pre-logit space
Sekitoshi Kanai, Tsukasa Yoshida, Hiroshi Takahashi +2
Test-time alignment of large language models (LLMs) attracts attention because fine-tuning of LLMs requires high computational costs. In this paper, we propose a new test-time rewa…
Evaluating Time-Series Training Dataset through Lens of Spectrum in Deep State Space Models
Sekitoshi Kanai, Yasutoshi Ida, Kazuki Adachi +3
This study investigates a method to evaluate time-series datasets in terms of the performance of deep neural networks (DNNs) with state space models (deep SSMs) trained on the data…
Adaptive Random Feature Regularization on Fine-tuning Deep Neural Networks
Shin'ya Yamaguchi, Sekitoshi Kanai, Kazuki Adachi +1
While fine-tuning is a de facto standard method for training deep neural networks, it still suffers from overfitting when using small target datasets. Previous methods improve fine…
Regularizing Neural Networks with Meta-Learning Generative Models
Shin'ya Yamaguchi, Daiki Chijiwa, Sekitoshi Kanai +2
This paper investigates methods for improving generative data augmentation for deep learning. Generative data augmentation leverages the synthetic samples produced by generative mo…
Fast Regularized Discrete Optimal Transport with Group-Sparse Regularizers
Yasutoshi Ida, Sekitoshi Kanai, Kazuki Adachi +2
Regularized discrete optimal transport (OT) is a powerful tool to measure the distance between two discrete distributions that have been constructed from data samples on two differ…
Fast Saturating Gate for Learning Long Time Scales with Recurrent Neural Networks
Kentaro Ohno, Sekitoshi Kanai, Yasutoshi Ida
Gate functions in recurrent models, such as an LSTM and GRU, play a central role in learning various time scales in modeling time series data by using a bounded activation function…
One-vs-the-Rest Loss to Focus on Important Samples in Adversarial Training
Sekitoshi Kanai, Shin'ya Yamaguchi, Masanori Yamada +3
This paper proposes a new loss function for adversarial training. Since adversarial training has difficulties, e.g., necessity of high model capacity, focusing on important data po…
Transfer Learning with Pre-trained Conditional Generative Models
Shin'ya Yamaguchi, Sekitoshi Kanai, Atsutoshi Kumagai +2
Transfer learning is crucial in training deep neural networks on new target tasks. Current transfer learning methods always assume at least one of (i) source and target task label…
Smoothness Analysis of Adversarial Training
Sekitoshi Kanai, Masanori Yamada, Hiroshi Takahashi +2
Deep neural networks are vulnerable to adversarial attacks. Recent studies about adversarial robustness focus on the loss landscape in the parameter space since it is related to op…