Image de couverture de livre

Bridging the Gap: Rademacher Complexity in Robust and Standard Generalization

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Xiao, Jiancong, Sun, Ruoyu, Long, Qi, Su, Weijie J.
Format:	Preprint
Publié:	2024
Sujets:	Machine Learning
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Theoretical Tensions in RLHF: Reconciling Empirical Success with Inconsistencies in Social Choice Theory
par: Xiao, Jiancong, et autres
Publié: (2025)

Fundamental Limits of Game-Theoretic LLM Alignment: Smith Consistency and Preference Matching
par: Shi, Zhekun, et autres
Publié: (2025)

Statistical Impossibility and Possibility of Aligning LLMs with Human Preferences: From Condorcet Paradox to Nash Equilibrium
par: Liu, Kaizhao, et autres
Publié: (2025)

On the Algorithmic Bias of Aligning Large Language Models with RLHF: Preference Collapse and Matching Regularization
par: Xiao, Jiancong, et autres
Publié: (2024)

Fine-Tuning Attention Modules Only: Enhancing Weight Disentanglement in Task Arithmetic
par: Jin, Ruochen, et autres
Publié: (2024)

Restoring Calibration for Aligned Large Language Models: A Calibration-Aware Fine-Tuning Approach
par: Xiao, Jiancong, et autres
Publié: (2025)

On Rademacher Complexity-based Generalization Bounds for Deep Learning
par: Truong, Lan V.
Publié: (2022)

A Gapped Scale-Sensitive Dimension and Lower Bounds for Offset Rademacher Complexity
par: Jia, Zeyu, et autres
Publié: (2025)

RCR-AF: Enhancing Model Generalization via Rademacher Complexity Reduction Activation Function
par: Yu, Yunrui, et autres
Publié: (2025)

Robust Spectral Watermark for Synthetic Tabular Data
par: Zhao, Yizhou, et autres
Publié: (2025)

Lean Formalization of Generalization Error Bound by Rademacher Complexity and Dudley's Entropy Integral
par: Sonoda, Sho, et autres
Publié: (2025)

Preserving Diversity in Supervised Fine-Tuning of Large Language Models
par: Li, Ziniu, et autres
Publié: (2024)

CurveRL: Principled Distribution-Aware Context Reweighting for LLM Reasoning
par: Sun, Ke, et autres
Publié: (2026)

Minimax Estimation for Personalized Federated Learning: An Alternative between FedAvg and Local Training?
par: Chen, Shuxiao, et autres
Publié: (2021)

Impact of Positional Encoding: Clean and Adversarial Rademacher Complexity for Transformers under In-Context Regression
par: He, Weiyi, et autres
Publié: (2025)

Rademacher Complexity of Neural ODEs via Chen-Fliess Series
par: Hanson, Joshua, et autres
Publié: (2024)

Robust Detection of Watermarks for Large Language Models Under Human Edits
par: Li, Xiang, et autres
Publié: (2024)

Towards Bridging the Reward-Generation Gap in Direct Alignment Algorithms
par: Xiao, Zeguan, et autres
Publié: (2025)

PolarGrad: A Class of Matrix-Gradient Optimizers from a Unifying Preconditioning Perspective
par: Lau, Tim Tsz-Kit, et autres
Publié: (2025)

Rademacher Meets Colors: More Expressivity, but at What Cost ?
par: Carrasco, Martin, et autres
Publié: (2025)

One-Step Early Stopping Strategy using Neural Tangent Kernel Theory and Rademacher Complexity
par: Xavier, Daniel Martin, et autres
Publié: (2024)

Do we really need the Rademacher complexities?
par: Bartl, Daniel, et autres
Publié: (2025)

Disentangled and Distilled Encoder for Out-of-Distribution Reasoning with Rademacher Guarantees
par: Rahiminasab, Zahra, et autres
Publié: (2025)

Uniformly Stable Algorithms for Adversarial Training and Beyond
par: Xiao, Jiancong, et autres
Publié: (2024)

De Novo Molecular Generation from Mass Spectra via Many-Body Enhanced Diffusion
par: Sun, Xichen, et autres
Publié: (2026)

Resilience of Rademacher chaos of low degree
par: Aigner-Horev, Elad, et autres
Publié: (2024)

Combinatorial Complexes: Bridging the Gap Between Cell Complexes and Hypergraphs
par: Hajij, Mustafa, et autres
Publié: (2023)

Mitigating Privacy-Utility Trade-off in Decentralized Federated Learning via $f$-Differential Privacy
par: Li, Xiang, et autres
Publié: (2025)

Improving the Trade-off Between Watermark Strength and Speculative Sampling Efficiency for Language Models
par: He, Weiqing, et autres
Publié: (2026)

Evaluating the Unseen Capabilities: How Many Theorems Do LLMs Know?
par: Li, Xiang, et autres
Publié: (2025)

Do Large Language Models (Really) Need Statistical Foundations?
par: Su, Weijie
Publié: (2025)

On the Empirical Power of Goodness-of-Fit Tests in Watermark Detection
par: He, Weiqing, et autres
Publié: (2025)

Bridging Formal Language with Chain-of-Thought Reasoning to Geometry Problem Solving
par: Yang, Tianyun, et autres
Publié: (2025)

Factor-MCLS: Multi-agent learning system with reward factor matrix and multi-critic framework for dynamic portfolio optimization
par: Sun, Ruoyu, et autres
Publié: (2025)

Bridging the Training-Inference Gap in LLMs by Leveraging Self-Generated Tokens
par: Cen, Zhepeng, et autres
Publié: (2024)

Bridging the Gap between Learning and Inference for Diffusion-Based Molecule Generation
par: Liu, Peidong, et autres
Publié: (2024)

A Statistical Viewpoint on Differential Privacy: Hypothesis Testing, Representation and Blackwell's Theorem
par: Su, Weijie J.
Publié: (2024)

Bridging the Theoretical Gap in Randomized Smoothing
par: Delattre, Blaise, et autres
Publié: (2025)

Dual-Forward Path Teacher Knowledge Distillation: Bridging the Capacity Gap Between Teacher and Student
par: Li, Tong, et autres
Publié: (2025)

Tackling Copyright Issues in AI Image Generation Through Originality Estimation and Genericization
par: Chiba-Okabe, Hiroaki, et autres
Publié: (2024)