4 papers
Asymptotic Analysis of Empirical Risk Minimization on Entry-wise i.i.d. Heavy-Tailed Data
Kaito Takanami, Takashi Takahashi, Yoshiyuki Kabashima
Many real-world datasets exhibit unusually large values far more frequently than predicted by Gaussian models. Heavy-tailed distributions capture this behavior, yet evaluating lear…
Analysis of the Hopfield Model Incorporating the Effects of Unlearning
Shuta Takeuchi, Takashi Takahashi, Yoshiyuki Kabashima
We analyze a variant of the Hopfield model that incorporates an unlearning mechanism based on spin correlations in the high-temperature regime. In the large system limit where exte…
Learning Linear Regression with Low-Rank Tasks in-Context
Kaito Takanami, Takashi Takahashi, Yoshiyuki Kabashima
In-context learning (ICL) is a key building block of modern large language models, yet its theoretical mechanisms remain poorly understood. It is particularly mysterious how ICL op…
Generating gradients in the energy landscape using rectified linear type cost functions for efficiently solving 0/1 matrix factorization in Simulated Annealing
Makiko Konoshima, Hirotaka Tamura, Yoshiyuki Kabashima
The 0/1 matrix factorization defines matrix products using logical AND and OR as product-sum operators, revealing the factors influencing various decision processes. Instances and…