Copertina

Provable Target Sample Complexity Improvements as Pre-Trained Models Scale

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Fukuchi, Kazuto, Hataya, Ryuichiro, Matsui, Kota
Natura:	Preprint
Pubblicazione:	2026
Soggetti:	Machine Learning
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Provable Data Scaling Law for Meta Learning via Complexity Minimization
di: Fukuchi, Kazuto, et al.
Pubblicazione: (2026)

Automatic Domain Adaptation by Transformers in In-Context Learning
di: Hataya, Ryuichiro, et al.
Pubblicazione: (2024)

Glocal Hypergradient Estimation with Koopman Operator
di: Hataya, Ryuichiro, et al.
Pubblicazione: (2024)

Meta Optimality for Demographic Parity Constrained Regression via Post-Processing
di: Fukuchi, Kazuto
Pubblicazione: (2025)

An Empirical Study of Pre-trained Model Selection for Out-of-Distribution Generalization and Calibration
di: Naganuma, Hiroki, et al.
Pubblicazione: (2023)

Noncommutative $C^*$-algebra Net: Learning Neural Networks with Powerful Product Structure in $C^*$-algebra
di: Hataya, Ryuichiro, et al.
Pubblicazione: (2023)

Quantum Circuit $C^*$-algebra Net
di: Hashimoto, Yuka, et al.
Pubblicazione: (2024)

Self-attention Networks Localize When QK-eigenspectrum Concentrates
di: Bao, Han, et al.
Pubblicazione: (2024)

Robust Deep Reinforcement Learning against Adversarial Behavior Manipulation
di: Yamabe, Shojiro, et al.
Pubblicazione: (2024)

Harnessing the Power of Vicinity-Informed Analysis for Classification under Covariate Shift
di: Fujikawa, Mitsuhiro, et al.
Pubblicazione: (2024)

Statistically Significant Concept-based Explanation of Image Classifiers via Model Knockoffs
di: Xu, Kaiwen, et al.
Pubblicazione: (2023)

Adversarial Attacks on Hidden Tasks in Multi-Task Learning
di: Zhe, Yu, et al.
Pubblicazione: (2024)

CAMRI Loss: Improving Recall of a Specific Class without Sacrificing Accuracy
di: Nishiyama, Daiki, et al.
Pubblicazione: (2022)

Provably Efficient Sample Complexity for Robust CMDP
di: Ganguly, Sourav, et al.
Pubblicazione: (2025)

Coherence Mechanisms for Provable Self-Improvement
di: Mohri, Mehryar, et al.
Pubblicazione: (2025)

Provably Convergent Subgraph-wise Sampling for Fast GNN Training
di: Wang, Jie, et al.
Pubblicazione: (2023)

Double Debiased Covariate Shift Adaptation Robust to Density-Ratio Estimation
di: Kato, Masahiro, et al.
Pubblicazione: (2023)

LMC: Fast Training of GNNs via Subgraph Sampling with Provable Convergence
di: Shi, Zhihao, et al.
Pubblicazione: (2023)

Provably Robust Pre-Trained Ensembles for Biomarker-Based Cancer Classification
di: Lee, Chongmin, et al.
Pubblicazione: (2024)

Dose-finding design based on level set estimation in phase I cancer clinical trials
di: Seno, Keiichiro, et al.
Pubblicazione: (2025)

An $(ε,δ)$-accurate level set estimation with a stopping criterion
di: Ishibashi, Hideaki, et al.
Pubblicazione: (2025)

Provable and Practical In-Context Policy Optimization for Self-Improvement
di: Yu, Tianrun, et al.
Pubblicazione: (2026)

Provable Complexity Improvement of AdaGrad over SGD: Upper and Lower Bounds in Stochastic Non-Convex Optimization
di: Jiang, Ruichen, et al.
Pubblicazione: (2024)

Provable Training for Graph Contrastive Learning
di: Yu, Yue, et al.
Pubblicazione: (2023)

Multi-modal cascade feature transfer for polymer property prediction
di: Obuchi, Kiichi, et al.
Pubblicazione: (2025)

Transformers Provably Implement In-Context Reinforcement Learning with Policy Improvement
di: Liang, Haodong, et al.
Pubblicazione: (2026)

Stochastic Extragradient with Flip-Flop Shuffling & Anchoring: Provable Improvements
di: Chae, Jiseok, et al.
Pubblicazione: (2024)

Provable Benefits of Unsupervised Pre-training and Transfer Learning via Single-Index Models
di: Jones-McCormick, Taj, et al.
Pubblicazione: (2025)

LaMM: Semi-Supervised Pre-Training of Large-Scale Materials Models
di: Oyama, Yosuke, et al.
Pubblicazione: (2025)

Provable Training Data Identification for Large Language Models
di: Liu, Zhenlong, et al.
Pubblicazione: (2025)

TFTF: Training-Free Targeted Flow for Conditional Sampling
di: Qu, Qianqian, et al.
Pubblicazione: (2026)

Limits of Generative Pre-Training in Structured EMR Trajectories with Irregular Sampling
di: Kuo, Nicholas I-Hsien, et al.
Pubblicazione: (2025)

FineInstructions: Scaling Synthetic Instructions to Pre-Training Scale
di: Patel, Ajay, et al.
Pubblicazione: (2026)

Domain Generalization Guided by Large-Scale Pre-Trained Priors
di: Wang, Zongbin, et al.
Pubblicazione: (2024)

Provable Unrestricted Adversarial Training without Compromise with Generalizability
di: Zhang, Lilin, et al.
Pubblicazione: (2023)

Provable Domain Adaptation for Offline Reinforcement Learning with Limited Samples
di: Chen, Weiqin, et al.
Pubblicazione: (2024)

Provably Sample-Efficient Robust Reinforcement Learning with Average Reward
di: Roch, Zachary, et al.
Pubblicazione: (2025)

Provable Privacy with Non-Private Pre-Processing
di: Hu, Yaxi, et al.
Pubblicazione: (2024)

Curvature Tuning: Provable Training-free Model Steering From a Single Parameter
di: Hu, Leyang, et al.
Pubblicazione: (2025)

Endowing Pre-trained Graph Models with Provable Fairness
di: Zhang, Zhongjian, et al.
Pubblicazione: (2024)