Quality follows upgrading
Ever a pioneer, ever a student — learning through our mistakes and failures
전체 전문분석자료
arXiv:2602.13348v1 Announce Type: new Abstract: Small datasets like MNIST have historically been instrumental in advancing machine learning research by providing a controlled environment for rapid …
arXiv:2602.13359v1 Announce Type: new Abstract: Machine learning models excel with abundant annotated data, but annotation is often costly and time-intensive. Active learning (AL) aims to …
arXiv:2602.13398v1 Announce Type: new Abstract: Designing cryoprotectant agent (CPA) cocktails for vitrification is challenging because formulations must be concentrated enough to suppress ice formation yet …
arXiv:2602.13413v1 Announce Type: new Abstract: We develop a worst-case complexity theory for stochastically preconditioned stochastic gradient descent (SPSGD) and its accelerated variants under heavy-tailed noise, …
arXiv:2602.13416v1 Announce Type: new Abstract: The proliferation of data-driven models in weather and climate sciences has marked a significant paradigm shift, with advanced models demonstrating …
arXiv:2602.13418v1 Announce Type: new Abstract: Does text have an intrinsic curvature? Language is increasingly modeled in curved geometries - hyperbolic spaces for hierarchy, mixed-curvature manifolds …
arXiv:2602.13482v1 Announce Type: new Abstract: Selecting an optimal classification model requires a robust and comprehensive understanding of the performance of the model. This paper provides …
arXiv:2602.13483v1 Announce Type: new Abstract: Understanding the internal circuits that language models use to solve tasks remains a central challenge in mechanistic interpretability. Most prior …
arXiv:2602.13485v1 Announce Type: new Abstract: Networks of modern industrial systems are increasingly monitored by distributed sensors, where each system comprises multiple subsystems generating high dimensional …
arXiv:2602.13486v1 Announce Type: new Abstract: Federated low-rank adaptation (FedLoRA) has facilitated communication-efficient and privacy-preserving fine-tuning of foundation models for downstream tasks. In practical federated learning …
arXiv:2602.13498v1 Announce Type: new Abstract: Muon-style optimizers leverage Newton-Schulz (NS) iterations to orthogonalize updates, yielding update geometries that often outperform Adam-series methods. However, this orthogonalization …
arXiv:2602.13506v1 Announce Type: new Abstract: Optimizing monotone non-convex functions is a fundamental challenge across machine learning and combinatorial optimization. We introduce and study $\gamma$-weakly $\theta$-up-concavity, …