1 citations · 1 across the 4 of their papers we have counts for
7 papers
QuSema: Detecting Silent Bugs in Quantum Libraries via Quantum-knowledge-enhanced Agents
Yujin Song, Kaining Zhang, Qixin Zhang +3
Quantum libraries are now critical infrastructure for quantum algorithm development, yet their correctness remains difficult to test. Existing testing techniques mainly rely on fai…
From Shortcut to Induction Head: How Data Diversity Shapes Algorithm Selection in Transformers
Ryotaro Kawata, Yujin Song, Alberto Bietti +4
Transformers can implement both generalizable algorithms (e.g., induction heads) and simple positional shortcuts (e.g., memorizing fixed output positions). In this work, we study h…
Sample-efficient quantum error mitigation via classical learning surrogates
Wei-You Liao, Ge Yan, Yujin Song +5
The pursuit of practical quantum utility on near-term quantum processors is critically challenged by their inherent noise. Quantum error mitigation (QEM) techniques are leading sol…
How Does Label Noise Gradient Descent Improve Generalization in the Low SNR Regime?
Wei Huang, Andi Han, Yujin Song +4
The capacity of deep learning models is often large enough to both learn the underlying statistical signal and overfit to noise in the training set. This noise memorization can be…
Pretrained transformer efficiently learns low-dimensional target functions in-context
Kazusato Oko, Yujin Song, Taiji Suzuki +1
Transformers can efficiently learn in-context from example demonstrations. Most existing theoretical analyses studied the in-context learning (ICL) ability of transformers for line…
Learning sum of diverse features: computational hardness and efficient gradient-based training for ridge combinations
Kazusato Oko, Yujin Song, Taiji Suzuki +1
We study the computational and sample complexity of learning a target function with additive structure, that is, $f_*(x) = \frac{1}{\sqrt{M}}\sum_{m…
Active Learning for the Optimal Design of Multinomial Classification in Physics
Yongcheng Ding, José D. Martín-Guerrero, Yujing Song +2
Optimal design for model training is a critical topic in machine learning. Active Learning aims at obtaining improved models by querying samples with maximum uncertainty according…