Tootfinder

Efficient Hyperparameter Tuning via Trajectory Invariance Principle
Bingrui Li, Jiaxin Wen, Zhanpeng Zhou, Jun Zhu, Jianfei Chen
https://arxiv.org/abs/2509.25049 https://…

Efficient Hyperparameter Tuning via Trajectory Invariance Principle
As hyperparameter tuning becomes increasingly costly at scale, efficient tuning methods are essential. Yet principles for guiding hyperparameter tuning remain limited. In this work, we seek to establish such principles by considering a broad range of hyperparameters, including batch size, learning rate, and weight decay. We identify a phenomenon we call trajectory invariance, where pre-training loss curves, gradient noise, and gradient norm exhibit invariance--closely overlapping--with respect …

🛰️ The Milky Way could be teeming with more satellite galaxies than previously thought
https://phys.org/news/2025-07-milky-teeming-satellite-galaxies-previously.html

The Milky Way could be teeming with more satellite galaxies than previously thought
The Milky Way could have many more satellite galaxies than scientists have previously been able to predict or observe, according to new research. Cosmologists at Durham University used a new technique combining the highest-resolution supercomputer simulations that exist, alongside novel mathematical modeling, to predict the existence of missing "orphan" galaxies.

from my link log —
Tuning async IO in PostgreSQL 18.
https://vondra.me/posts/tuning-aio-in-postgresql-18/
saved 2025-09-26 https://

Federated Fine-tuning of SAM-Med3D for MRI-based Dementia Classification
Kaouther Mouheb, Marawan Elbatel, Janne Papma, Geert Jan Biessels, Jurgen Claassen, Huub Middelkoop, Barbara van Munster, Wiesje van der Flier, Inez Ramakers, Stefan Klein, Esther E. Bron
https://arxiv.org/abs/2508.21458

Federated Fine-tuning of SAM-Med3D for MRI-based Dementia Classification
While foundation models (FMs) offer strong potential for AI-based dementia diagnosis, their integration into federated learning (FL) systems remains underexplored. In this benchmarking study, we systematically evaluate the impact of key design choices: classification head architecture, fine-tuning strategy, and aggregation method, on the performance and efficiency of federated FM tuning using brain MRI data. Using a large multi-cohort dataset, we find that the architecture of the classification…

Not All Parameters Are Created Equal: Smart Isolation Boosts Fine-Tuning Performance
Yao Wang, Di Liang, Minlong Peng
https://arxiv.org/abs/2508.21741 https://

Not All Parameters Are Created Equal: Smart Isolation Boosts Fine-Tuning Performance
Supervised fine-tuning (SFT) is a pivotal approach to adapting large language models (LLMs) for downstream tasks; however, performance often suffers from the ``seesaw phenomenon'', where indiscriminate parameter updates yield progress on certain tasks at the expense of others. To address this challenge, we propose a novel \emph{Core Parameter Isolation Fine-Tuning} (CPI-FT) framework. Specifically, we first independently fine-tune the LLM on each task to identify its core parameter regions by q…

zkLoRA: Fine-Tuning Large Language Models with Verifiable Security via Zero-Knowledge Proofs
Guofu Liao, Taotao Wang, Shengli Zhang, Jiqun Zhang, Shi Long, Dacheng Tao
https://arxiv.org/abs/2508.21393 …

zkLoRA: Fine-Tuning Large Language Models with Verifiable Security via Zero-Knowledge Proofs
Fine-tuning large language models (LLMs) is crucial for adapting them to specific tasks, yet it remains computationally demanding and raises concerns about correctness and privacy, particularly in untrusted environments. Although parameter-efficient methods like Low-Rank Adaptation (LoRA) significantly reduce resource requirements, ensuring the security and verifiability of fine-tuning under zero-knowledge constraints remains an unresolved challenge. To address this, we introduce zkLoRA, the fi…

TR-PTS: Task-Relevant Parameter and Token Selection for Efficient Tuning
Siqi Luo, Haoran Yang, Yi Xin, Mingyang Yi, Guangyang Wu, Guangtao Zhai, Xiaohong Liu
https://arxiv.org/abs/2507.22872

TR-PTS: Task-Relevant Parameter and Token Selection for Efficient Tuning
Large pre-trained models achieve remarkable performance in vision tasks but are impractical for fine-tuning due to high computational and storage costs. Parameter-Efficient Fine-Tuning (PEFT) methods mitigate this issue by updating only a subset of parameters; however, most existing approaches are task-agnostic, failing to fully exploit task-specific adaptations, which leads to suboptimal efficiency and performance. To address this limitation, we propose Task-Relevant Parameter and Token Select…

from my link log —
Timing conclusions: GPS, NTP, PTP timing with Linux.
https://scottstuff.net/posts/2025/06/10/timing-conclusions/
saved 2025-08-25

Timing Conclusions
This is the 13th article that I’ve written lately on NTP and PTP timing with Linux. I set out to answer a couple questions for myself and ended up spending two months swimming in an ocean of nanosecond-scale measurements. When I started, I saw a lot of misinformation about NTP and PTP online. Things like: Conventional wisdom said that NTP was good for millisecond-scale timing accuracy. I expected that to be rather pessimistic, and expected to see low microsecond to high nanosecond-range synci…

BALF: Budgeted Activation-Aware Low-Rank Factorization for Fine-Tuning-Free Model Compression
David Gonz\'alez Mart\'inez
https://arxiv.org/abs/2509.25136 https://

BALF: Budgeted Activation-Aware Low-Rank Factorization for Fine-Tuning-Free Model Compression
Neural network compression techniques typically require expensive fine-tuning or search procedures, rendering them impractical on commodity hardware. Inspired by recent LLM compression research, we present a general activation-aware factorization framework that can be applied to a broad range of layers. Moreover, we introduce a scalable budgeted rank allocator that allows flexible control over compression targets (e.g., retaining 50% of parameters) with no overhead. Together, these components f…