activity
20242026
collaborators
Showing stat.MLShow all

5 papers · 1 filter

stat.ML2025

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…

stat.ML2025

Continuous Parallel Relaxation for Finding Diverse Solutions in Combinatorial Optimization Problems

Yuma Ichikawa, Hiroaki Iwashita

Finding the optimal solution is often the primary goal in combinatorial optimization (CO). However, real-world applications frequently require diverse solutions rather than a singl…

stat.ML2025

High-dimensional Asymptotics of VAEs: Threshold of Posterior Collapse and Dataset-Size Dependence of Rate-Distortion Curve

Yuma Ichikawa, Koji Hukushima

In variational autoencoders (VAEs), the variational posterior often collapses to the prior, known as posterior collapse, which leads to poor representation learning quality. An adj…

stat.ML2024

Controlling Continuous Relaxation for Combinatorial Optimization

Yuma Ichikawa

Unsupervised learning (UL)-based solvers for combinatorial optimization (CO) train a neural network that generates a soft solution by directly optimizing the CO objective using a c…

stat.ML2024

Ratio Divergence Learning Using Target Energy in Restricted Boltzmann Machines: Beyond Kullback--Leibler Divergence Learning

Yuichi Ishida, Yuma Ichikawa, Aki Dote +2

We propose ratio divergence (RD) learning for discrete energy-based models, a method that utilizes both training data and a tractable target energy function. We apply RD learning t…