◍wovepaper
SearchResearchersInstitutions
Sign in
researcher

Taiji Suzuki

13 papers hereh-index 10459 citations18 works total

Matching runs newest-first, so older work may not be attached to this profile yet.

author position
  • middle author6
  • last author7

Across the 13 of 13 papers where every author was matched, so the position is known.

fields
  • cs.LG5
  • stat.ML4
  • math.OC2
  • cs.AI1
  • cs.CL1
same name
  • Taiji Suzuki — 16 papers, h 5
  • Taiji Suzuki — 9 papers, h 4
  • Taiji Suzuki — 7 papers, h 1
  • Taiji Suzuki — 5 papers, h 6
  • Taiji Suzuki — 5 papers, h 3
  • Taiji Suzuki — 4 papers, h 2

Either other researchers who publish under this name, or the same person where the external sources have not merged their records.

identity via Semantic Scholar / OpenAlex

collaborators
Showing stat.MLShow all

4 papers · 1 filter

stat.ML2025

Optimality and Adaptivity of Deep Neural Features for Instrumental Variable Regression

Juno Kim, Dimitri Meunier, Arthur Gretton +2

We provide a convergence analysis of deep feature instrumental variable (DFIV) regression (Xu et al., 2021), a nonparametric approach to IV regression using data-adaptive features…

stat.ML2024

Transformers are Minimax Optimal Nonparametric In-Context Learners

Juno Kim, Tai Nakamaki, Taiji Suzuki

In-context learning (ICL) of large language models has proven to be a surprisingly effective method of learning a new task from only a few demonstrative examples. In this paper, we…

stat.ML2024

High-Dimensional Kernel Methods under Covariate Shift: Data-Dependent Implicit Regularization

Yihang Chen, Fanghui Liu, Taiji Suzuki +1

This paper studies kernel ridge regression in high dimensions under covariate shifts and analyzes the role of importance re-weighting. We first derive the asymptotic expansion of h…

stat.ML2024

Transformers Learn Nonlinear Features In Context: Nonconvex Mean-field Dynamics on the Attention Landscape

Juno Kim, Taiji Suzuki

Large language models based on the Transformer architecture have demonstrated impressive capabilities to learn in context. However, existing theoretical studies on how this phenome…

◍wovepaper

Papers, researchers and institutions, woven together.

Explore
  • Search
  • Researchers
  • Institutions
Account
  • Library
  • Chat
Data
  • arXiv.org
  • Semantic Scholar
  • OpenAlex
  • Latest RSS
AboutContactPrivacyDevelopersllms.txtopenapi.json
Not affiliated with arXiv. Researcher data from Semantic Scholar (ODC-BY) and OpenAlex.