Portrait of Hiroki Naganuma (長沼 大樹)

Hiroki Naganuma

Research Engineer, NVIDIAVisiting Assistant Prof, Keio University

Hiroki Naganuma is a Research Engineer at NVIDIA, where he works on efficient pretraining algorithms and the pretraining of Nemotron models, and has a Visiting Assistant Professor appointment at Keio University beginning in late 2026. His research covers large-scale optimization, distributed deep learning, and efficient training of large language models.

Ph.D. thesis: Toward Efficient and Scalable Optimization: Theoretical Insights and Practical Challenges

hiroki11x@gmail.com · ORCID · Google Scholar · alphaXiv · researchmap · J-GLOBAL

News

Research areas

Research overview and supporting publications

Selected and recent publications

  1. Understanding Stability of Outer Nesterov Momentum on Stochastic Pseudo-Gradients — arXiv (2026)

    arXivpdfX post

  2. Which Geometry on Which Layer? Measured Sign-Spectral Assignment in Mixed-Optimizer Training — arXiv (2026)

    arXivpdf

  3. Generalization Measures under Controlled Covariate Shift: A Regime-Aware Benchmark — TMLR 2026 (2026)

    arXivX post

  4. Adaptive Batch Sizes Using Non-Euclidean Gradient Noise Scales for Stochastic Sign and Spectral Descent — ICML 2026 (2026)

    arXivconferenceposterX post

  5. What do near-optimal learning rate schedules look like? — TMLR 2026 (2026)

    arXivX post

  6. Orth-Dion: Eliminating Geometric Mismatch in Distributed Low-Rank Spectral Optimization — Under Review (2026)

    arXivX post

  7. The Geometry of Spectral Gradient Descent: Layerwise Criteria for SignSGD vs SpecSGD — ICLR 2026 Workshop (2026)

    X post

  8. On Fairness of Task Arithmetic: The Role of Task Vectors — ICLR 2026 (2026)

    arXivcodeconferenceslidesposterX post

  9. DisTaC: Conditioning Task Vectors via Distillation for Robust Model Merging — ICLR 2026 (2026)

    arXivcodeconferenceslidesposterX post

  10. Pseudo-Asynchronous Local SGD: Robust and Efficient Data-Parallel Training — TMLR 2025 (2025)

    arXivcodeX post

View all publications

Curriculum vitae (PDF) / Detailed Biography